About     Design and AI     Writings     SxD Blog

Arxiv Whitepaper Links

Here's a list of whitepapers I have read and excerpted for myself. I have focused on conversational AI and LLMs, with particular interest in LLM cognitive architectures, reasoning, agent frameworks, and uses of LLMs in recommendations, question-answer search, chatbots, and interaction. I approached these papers with an interest in opportunties for design as a framework for interaction with generative AI. I have all these whitepapers downloaded and highlighted, as well as another one thousand that I read but haven't excerpted.

AI Agents

Large Language Model-Brained GUI Agents: A Survey
CAMEL Communicative Agents For “Mind” Exploration Of Large Language Model Society
Voyager: An Open-Ended Embodied Agent with Large Language Models
Openagents: An Open Platform For Language Agents In The Wild
Automated Design of Agentic Systems
Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization
Octopus v4: Graph of language models
Octopus v2: On-device language model for super agent
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents
Turn Every Application into an Agent: Towards Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
Language Agents as Optimizable Graphs Interaction
Agents Are Not Enough

Multi-Agent Models and Frameworks

Metagpt: Meta Programming For Multi-agent Collaborative Framework
Unleashing Cognitive Synergy In Large Language Models: A Task-solving Agent Through Multi-persona Self-collaboration
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents
CGMI: Configurable General Multi-Agent Interaction Framework
Generative Agents: Interactive Simulacra of Human Behavior
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
Apollo's Oracle: Retrieval-Augmented Reasoning in Multi-Agent Debates
A Domain Specific Modeling Language for Multiagent Systems
PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods
Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems
ProAgent: Building Proactive Cooperative Agents with Large Language Models
Adapting LLM Agents with Universal Feedback in Communication
The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation
Agent-as-a-Judge: Evaluate Agents with Agents
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Agent Laboratory: Using LLM Agents as Research Assistants
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

LLM Alignment

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants
LIMA: Less Is More for Alignment
OpenAssistant Conversations - Democratizing Large Language Model Alignment
A Survey of Meta-Reinforcement Learning
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Simple Synthetic Data Reduces Sycophancy In Large Language Models
Using Natural Language for Reward Shaping in Reinforcement Learning
Better Alignment with Instruction Back-and-Forth Translation
Self-Alignment with Instruction Backtranslation
KTO: Model Alignment as Prospect Theoretic Optimization
Beyond Preferences in AI Alignment

LLM Reasoning as Argumentation

LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback DR-HAI: Argumentation-based Dialectical Reconciliation in Human-AI Interactions
How susceptible are LLMs to Logical Fallacies?
The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants
A Hybrid Human-AI Approach for Argument Map Creation From Transcripts
A Hybrid Intelligence Method for Argument Mining
A Robustness Evaluation Framework for Argument Mining
Argument Quality Assessment in the Age of Instruction-Following Large Language Models
Modeling Appropriate Language in Argumentation
Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing
The Place of Emotion in Argument
Can Language Models Recognize Convincing Arguments?
Exploring the Potential of Large Language Models in Computational Argumentation
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
Debating with More Persuasive LLMs Leads to More Truthful Answers
Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying
Argumentative Large Language Models for Explainable and Contestable Decision-Making

AI Assistants and Personalization

Learning To Guide Human Experts Via Personalized Large Language Models
Personalization of Large Language Models: A Survey
Personalized Dialogue Generation with Persona-Adaptive Attention
Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations
Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting

Cowriting and Collaboration with AI

GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency
DATATALES: Investigating the use of Large Language Models for Authoring Data-Driven Articles
TaleStream: Supporting Story Ideation with Trope Knowledge
“It Felt Like Having a Second Mind”: Investigating Human-AI Co-creativity in Prewriting with Large Language Models
DOC: Improving Long Story Coherence With Detailed Outline Control
Controlling Linguistic Style Aspects in Neural Language Generation
A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts
AI-Powered (Finance) Scholarship

Cognitive Models for Generative AI

Turning large language models into cognitive models
In-context learning agents are asymmetric belief updaters
Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks
Mastering Diverse Domains through World Models
Large language models can segment narrative events similarly to humans
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
Thinking LLMs: General Instruction Following with Thought Generation
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
Latent Skill Discovery for Chain-of-Thought Reasoning
Diffusion Models are Evolutionary Algorithms
Large Language Models Reflect the Ideology of their Creators
Training Large Language Models to Reason in a Continuous Latent Space
A polar coordinate system represents syntax in large language models
Understanding Hidden Computations in Chain-of-Thought Reasoning
Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents
ACE: Abstractions for Communicating Efficiently
Nested Attention: Semantic-aware Attention Values for Concept Personalization

Conversational Agents

TREC iKAT 2023: A Test Collection for Evaluating Conversational and Interactive Knowledge Assistants
Towards Human-centered Proactive Conversational Agents
Rethinking Conversational Agents in the Era of LLMs: Proactivity, Non-collaborativity, and Beyond
Proactive Conversational Agents in the Post-ChatGPT World
Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Conversational Agents: Architecture and Structure

Towards Conversational Recommendation over Multi-Type Dialogs
OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs
Proactive Human-Machine Conversation with Explicit Conversation Goals
A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects
ProsocialDialog: A Prosocial Backbone for Conversational Agents
Pro-Active Systems and Influenceable Users: Simulating Pro-Activity in Task-oriented Dialogues
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration
Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations
Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
KETOD: Knowledge-Enriched Task-Oriented Dialogue
A Socially-Aware Conversational Recommender System for Personalized Recipe Recommendations
Cognitive Architectures for Language Agents
Insert-expansions For Tool-enabled Conversational Agents
Sequence Organization in Interaction: A Primer in Conversation Analysis
Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models
Learning to Relate to Previous Turns in Conversational Search
Learning to Select the Relevant History Turns in Conversational Question Answering

Conversation Topics and Dialogical Agents

Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
Dialog Inpainting: Turning Documents into Dialogs
Evaluating Emotional Nuances In Dialogue Summarization
MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
OpinionConv: Conversational Product Search with Grounded Opinions
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
DAPIE: Interactive Step-by-Step Explanatory Dialogues to Answer Children’s
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
Characterizing Online Discussion Using Coarse Discourse Sequences
Prompted LLMs as Chatbot Modules for Long Open-domain Conversation
Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
Target-Guided Open-Domain Conversation
Lexical Entrainment for Conversational Systems
Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues
Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification
Empirical Study of Symmetrical Reasoning in Conversational Chatbots
Learning Retrieval Augmentation for Personalized Dialogue Generation
Modeling the Quality of Dialogical Explanations
“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations
Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations
SDPO: Segment-Level Direct Preference Optimization for Social Agents

Decision Support AI Systems

Determinants of LLM-assisted Decision-Making
Building Decision Making Models Through Language Model Regime
DeLLMa: Decision Making Under Uncertainty with Large Language Models
Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than Answering
Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate

Design Frameworks for Generative AI

Design Principles for Generative AI Applications
See you soon again, chatbot? A design taxonomy to characterize user-chatbot relationships with different time horizons
Large Language Models for User Interest Journeys
Towards Algorithmic Experience
Building a Stronger CASA: Extending the Computers Are Social Actors Paradigm
Considering the Context to Build Theory in HCI, HRI, and HMC: Explicating Differences in Processes of Communication and
Social Responses to Media Technologies in the 21st Century: The Media are Social Actors Paradigm
An extended framework for characterizing social robots
Social Robots for Long-Term Interaction: A Survey
Virtual Assistance in Any Context
Proactive behavior in voice assistants: A systematic review and conceptual model
Opportunities for large language models and discourse in engineering design
Systematic synthesis of design prompts for large language models in conceptual design
Conceptual Design Generation Using Large Language Models
How well can large language models explain business processes?
Trust in Human-AI Interaction: Scoping Out Models, Measures, and Methods
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

Discourse Theory and Generative AI

Attention, Intentions, And The Structure Of Discourse
Pretrained Language Models as Containers of the Discursive Knowledge
The Hermeneutics of Artificial Text
Theory of Knowledge Based on the Idea of the Discursive Space
Semantic Change Characterization with LLMs using Rhetorics
What is a Discourse Graph?

Domain Specialization and LLMs

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Empowering Domain-Specific Language Models with Graph-Oriented Databases: A Paradigm Shift in Performance and Model Maintenance
Harnessing Business and Media Insights with Large Language Models
Scaling Expert Language Models with Unsupervised Domain Discovery
Domain-specific Question Answering with Hybrid Search
On The Persona-based Summarization of Domain-Specific Documents

Education and Generative AI

Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media
Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12
"Is ChatGPT a Better Explainer than My Professor?": Evaluating the Explanation Capabilities of LLMs in Conversation Compared to
GPT-4 as a Homework Tutor can Improve Student Engagement and Learning Outcomes
AI Meets the Classroom: When Does ChatGPT Harm Learning?

Evaluations and LLMs

Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools
Off-Policy Evaluation for Large Action Spaces via Policy Convolution
Large language models surpass human experts in predicting neuroscience results
A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions

Flaws in LLMs

Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions
A Survey on Concept Drift Adaptation
A comprehensive analysis of concept drift locality in data streams
Are Emergent Abilities of Large Language Models a Mirage?
Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
Investigating Gender Bias in Language Models Using Causal Mediation Analysis
Hallucination is Inevitable: An Innate Limitation of Large Language Models
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
Long-form Factuality In Large Language models
Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words

Knowledge Graphs and LLMs

Large Language Models and Knowledge Graphs: Opportunities and Challenges
Exploring Large Language Models for Knowledge Graph Completion
Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
ChatGPT is not Enough: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling
Intrinsically Motivated Graph Exploration Using Network Theories of Human Curiosity
Informed Named Entity Recognition Decoding For Generative Language Models
Knowledge Graph Prompting for Multi-Document Question Answering
JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Schema-learning and rebinding as mechanisms of in-context learning and emergence
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model with Knowledge Graph
Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought
StructGPT: A General Framework for Large Language Model to Reason over Structured Data
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
From Louvain to Leiden: guaranteeing well-connected communities
Can Language Models Solve Graph Problems in Natural Language?
Talk like a Graph: Encoding Graphs for Large Language Models
MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
Interesting Scientific Idea Generation Using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Causal Claims in Economics

LLM Architecture

The Unreasonable Ineffectiveness of the Deeper Layers
Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?
Progress Measures For Grokking Via Mechanistic Interpretability
Retrieval Head Mechanistically Explains Long-Context Factuality
Holy Grail 2.0: From Natural Language to Constraint Models
Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework
What are the Goals of Distributional Semantics?
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Probing Structured Semantics Understanding and Generation of Language Models via Question Answering
Discovering Latent Concepts Learned in BERT
On the Binding Problem in Artificial Neural Networks
A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
Deep Neural Network Approach for the Dialog State Tracking Challenge
Neural Approaches to Conversational AI
SParC: Cross-Domain Semantic Parsing in Context
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
Textgrad: Automatic “Differentiation” via Text
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Can Language Models Serve as Text-Based World Simulators?
System 1 vs. System 2 Thinking
Detecting hallucinations in large language models using semantic entropy
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
Faith and Fate: Limits of Transformers on Compositionality
Large Language Model Programs
Neurosymbolic AI- Why, What, and How
Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
Are Emergent Abilities in Large Language Models just In-Context Learning?
UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity
Everything Everywhere All At Once: Llms Can In-context Learn Multiple Tasks In Superposition
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Self-reinforcing cascades: A spreading model for beliefs or products of varying intensity or quality
Byte Latent Transformer:  Patches Scale Better Than Tokens
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Titans: Learning to Memorize at Test Time
All AI Models are Wrong, but Some are Optimal
All AI Models are Wrong, but Some are Optimal
Transformer2: Self-adaptive LLMs
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Multimodal AI

Large Multimodal Agents: A Survey
Mindstorms in Natural Language-Based Societies of Mind
Explainable Multimodal Emotion Reasoning
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Personas and Personality of Generative AI

Generative Agent Simulations of 1,000 People
CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models
Cognitive Effects in Large Language Models
EmotionPrompt: Leveraging Psychology for Large Language Models Enhancement via Emotional Stimulus
Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models
PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer
Improving Dialog Systems for Negotiation with Personality Modeling
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Understanding the Role of User Profile in the Personalization of Large Language Models
Large Language Models Can Infer Psychological Dispositions of Social Media Users
Using Large Language Models to Create AI Personas for Replication and Prediction of Media Effects: An Empirical Test of 133
Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Design
Proxona: Leveraging LLM-Driven Personas to Enhance Creators' Understanding of Their Audience
Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models
Chamain: Harmonizing Character Persona Integrity with Domain-Adaptive Knowledge in Dialogue Generation
PersonaGym: Evaluating Persona Agents and LLMs
Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
Unlocking Varied Perspectives: A Persona-Based Multi-Agent Framework with Debate-Driven Text Planning for Argument Generation
Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations
PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological

Philosophy and Subjectivity in LLMs

Language Models are Pragmatic Speakers
Are you in a Masquerade? Exploring the Behavior and Impact of Large Language Model Driven Social Bots in Online Social Networks
Talking About Large Language Models
ChatGPT: towards AI subjectivity
ChatGPT: deconstructing the debate and moving it forward
A sociotechnical perspective for the future of AI: narratives, inequalities, and human control
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Find the Gap: AI, Responsible Agency and Vulnerability
The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom
When Large Language Models contradict humans? Large Language Models’ Sycophantic Behaviour
“Understanding AI”: Semantic Grounding in Large Language Models
Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments
The Vector Grounding Problem
Grounding ‘Grounding’ in NLP
A recipe for annotating grounded clarifications
We’re Afraid Language Models Aren’t Modeling Ambiguity
Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?
Polanyi’s Revenge and AI’s New Romance with Tacit Knowledge
Expedient Assistance and Consequential Misunderstanding: Envisioning an Operationalized Mutual Theory of Mind
Machine gaze in online behavioral targeting: The effects of algorithmic human likeness on social presence and social influence
Chatbot vs. Human: The Impact of Responsive Conversational Features on Users’ Responses to Chat Advisors
Machine ex machina: A Framework Decentering the Human in AI Design Praxis
Goals, Plans, and Action Models
Machine Psychology
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
Dissociating language and thought in large language models
Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency
AI Enters Public Discourse: A Habermasian Assessment Of The Moral Status Of Large Language Models
The Method of Critical AI Studies, A Propaedeutic
Simulacra as conscious exotica
Existential Conversations with Large Language Models: Content, Community, and Culture
Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responses
Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models

Prompts and Prompting with LLMs

Prefix-Tuning: Optimizing Continuous Prompts for Generation
From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
Skills-in-context Prompting: Unlocking Compositionality In Large Language Models
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
Attribute Controlled Dialogue Prompting
Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation
Metacognitive Prompting Improves Understanding in Large Language Models
Re3: Generating Longer Stories With Recursive Reprompting and Revision
Instruction Induction: From Few Examples to Natural Language Task Descriptions
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Do Prompt-Based Models Really Understand the Meaning of Their Prompts?
The Prompt Report: A Systematic Survey of Prompting Techniques
Conversational Prompt Engineering
Instance-adaptive Zero-shot Chain-of-Thought Prompting
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
Progressive-Hint Prompting Improves Reasoning in Large Language Models
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Large Language Models Are Human-level Prompt Engineers
Boosted Prompt Ensembles for Large Language Models
Learning To Retrieve Prompts for In-Context Learning
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Dynamic Prompting: A Unified Framework for Prompt Tuning
KiPT: Knowledge-injected Prompt Tuning for Event Detection
Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?
ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Ask, and it shall be given: Turing completeness of prompting
From Prompt Engineering to Prompt Science With Human in the Loop

Psychology of Chatbots and Conversational AI

Can an LLM-Powered Socially Assistive Robot Effectively and Safely Deliver Cognitive Behavioral Therapy? A Study With
Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot’s Self-Disclosure in Conversational Recommendations
The Partner Modelling Questionnaire: A validated self-report measure of perceptions toward machines as dialogue partners
Modeling Interpersonal Linguistic Coordination in Conversations using Word Mover's Distance
IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
Evidence of Human-Level Bonds Established With a Digital Conversational Agent: Cross-sectional, Retrospective Observational
Supporting Physical Activity Behavior Change with LLM-Based Conversational Agents
The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study
Towards Healthy AI: Large Language Models Need Therapists Too
Working Alliance Transformer for Psychotherapy Dialogue Classification
Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
A Computational Framework for Behavioral Assessment of LLM Therapists
LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart
Revolutionizing Mental Health Support: An Innovative Affective Mobile Framework for Dynamic, Proactive, and Context-Adaptive
Can robots do therapy?: Examining the efficacy of a CBT bot in comparison with other behavioral intervention technologies in
VCounselor: A Psychological Intervention Chat Agent Based on a Knowledge-Enhanced Large Language Model
From speaking like a person to being personal: The effects of personalized, regular interactions with conversational agents
Psychological, Relational, and Emotional Effects of Self-Disclosure After Conversations With a Chatbot
Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot’s Self-Disclosure in Conversational Recommendations
The Partner Modelling Questionnaire: A validated self-report measure of perceptions toward machines as dialogue partners
Modeling Interpersonal Linguistic Coordination in Conversations using Word Mover's Distance
IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
Evidence of Human-Level Bonds Established With a Digital Conversational Agent: Cross-sectional, Retrospective Observational
Supporting Physical Activity Behavior Change with LLM-Based Conversational Agents
The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study
Towards Healthy AI: Large Language Models Need Therapists Too
Working Alliance Transformer for Psychotherapy Dialogue Classification
Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
A Computational Framework for Behavioral Assessment of LLM Therapists
LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart
Revolutionizing Mental Health Support: An Innovative Affective Mobile Framework for Dynamic, Proactive, and Context-Adaptive
Can robots do therapy?: Examining the efficacy of a CBT bot in comparison with other behavioral intervention technologies in
VCounselor: A Psychological Intervention Chat Agent Based on a Knowledge-Enhanced Large Language Model
From speaking like a person to being personal: The effects of personalized, regular interactions with conversational agents
Psychological, Relational, and Emotional Effects of Self-Disclosure After Conversations With a Chatbot

Psychology and Empathy in Generative AI

Study: Large language models can’t effectively recognize users’ motivation, but can support behavior change for those ready to
Inducing Positive Perspectives with Text Reframing
Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems
Topic Modeling in Embedding Spaces
Large Language Models Understand and Can be Enhanced by Emotional Stimuli
Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support
Empathy Through Multimodality in Conversational Interfaces
Computer says “No”: The Case Against Empathetic Conversational AI
A Taxonomy of Empathetic Questions in Social Dialogs
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
To Tell The Truth: Language of Deception and Language Models
ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context
Rise of Machine Agency: A Framework for Studying the Psychology of Human–AI Interaction (HAII)

Psychology and AI in Therapeutic Practices

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation
Using Linguistic Synchrony to Evaluate Large Language Models for Cognitive Behavioral Therapy
Evaluating the Efficacy of Interactive Language Therapy Based on LLM for High-Functioning Autistic Adolescent Psychological
Challenges of Large Language Models for Mental Health Counseling
Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics
COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modeling
SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning
Neural Topic Modeling of Psychotherapy Sessions
Measuring Alliance and Symptom Severity in Psychotherapy Transcripts Using Bert Topic Modeling
A natural language processing approach reveals first-person pronoun usage and non-fluency as markers of therapeutic alliance in
Using Topic Models to Identify Clients’ Functioning Levels and Alliance Ruptures in Psychotherapy
Prospective evaluation of a clinical decision support system in psychological therapy
The Digital Therapeutic Alliance: Prospects and Considerations
The Digital Therapeutic Alliance and Human-Computer Interaction
PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals
Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting
Detecting Cognitive Distortions from Patient-Therapist Interactions
Rethinking Large Language Models in Mental Health Applications
Evaluating the Therapeutic Alliance With a Free-Text CBT Conversational Agent (Wysa): A Mixed-Methods Study

Psychology of Users of AI

Understanding, explaining, and utilizing medical artificial intelligence
Comparing emotion feature extraction approaches for predicting depression and anxiety
Discourse-Level Representations can Improve Prediction of Degree of Anxiety

Question-Answer Search and AI

Generator-Retriever-Generator: A Novel Approach to Open-domain Question Answering
Query Understanding in the Age of Large Language Models
Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search
Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games
No that's not what I meant: Handling Third Position Repair in Conversational Question Answering
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
Asking Clarifying Questions Based on Negative Feedback in Conversational Search
Topic Shift Detection for Mixed Initiative Response
Learning to Ask Critical Questions for Assisting Product Search
Learning to Ask Appropriate Questions in Conversational Recommendation
Structured and Natural Responses Co-generation for Conversational Search
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions
Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
Stream of Search (SoS): Learning to Search in Language
Knowledge Retrieval Based on Generative AI

RAG Methods

Leveraging LLMs for KPIs Retrieval from Hybrid Long-Document: A Comprehensive Framework and Dataset
Context Tuning for Retrieval Augmented Generation
Precise Zero-Shot Dense Retrieval without Relevance Labels
Dense Retrieval Adaptation using Target Domain Description
Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System
Active Retrieval Augmented Generation
Context Tuning for Retrieval Augmented Generation
RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
RAG Does Not Work for Enterprises
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Searching for Best Practices in Retrieval-Augmented Generation
Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
The Insanity of Relying on Vector Embeddings: Why RAG Fails

Reading and Summarizing with LLMs

Assessing the Ability of ChatGPT to Screen Articles for Systematic Reviews
From Key Points to Key Point Hierarchy: Structured and Expressive Opinion Summarization
Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization
Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system

Reasoning Architectures of LLMs

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Flows: Building Blocks of Reasoning and Collaborating AI
React - Synergizing Reasoning And Acting In Language Models
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
Efficient Tool Use with Chain-of-Abstraction Reasoning
Can large language models explore in-context?
Strategic Reasoning with Language Models
Generalization to New Sequential Decision Making Tasks with In-Context Learning
𝙻𝙼𝟸: A Simple Society of Language Models Solves Complex Reasoning
Improving Factuality and Reasoning in Language Models through Multiagent Debate
Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Thinking Forward and Backward: Effective Backward Planning with Large Language Models
Reverse Thinking Makes LLMs Stronger Reasoners
Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models

Reasoning by Reflection in LLMs

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Reflexion: an autonomous agent with dynamic memory and self-reflection
System 2 Attention (is something you might need too)
SELF-INSTRUCT: Aligning Language Models with Self-Generated Instructions
Teaching Large Language Models to Reason with Reinforcement Learning
Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Reasoning Logic Internal to LLMs

Can LLMs Follow Simple Rules?
Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting
Abductive Reasoning with the GPT-4 Language Model: Case studies from criminal investigation, medical practice, scientific
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
Complexity-Based Prompting for Multi-Step Reasoning
Can Large Language Models Understand Context?
Premise Order Matters in Reasoning with Large Language Models
An Overview Of Temporal Commonsense Reasoning and Acquisition
Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability
Reasoning with Large Language Models, a Survey
Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Chain of Thoughtlessness? An Analysis of CoT in Planning
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning

Reasoning Methods in LLMS: CoT, ToT, Graph of Thought, etc.

Measuring Faithfulness in Chain-of-Thought Reasoning
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine
Least-to-most Prompting Enables Complex Reasoning In Large Language Models
Large Language Model Guided Tree-of-Thought
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data
Self-consistency Improves Chain Of Thought Reasoning In Language Models
Chain-of-thought Reasoning Is A Policy Improvement Operator
Break the Chain: Large Language Models Can be Shortcut Reasoners
Multi-hop Question Answering via Reasoning Chains
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
Demystifying Chains, Trees, and Graphs of Thoughts
Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
Cumulative Reasoning with Large Language Models
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought

Reasoning in o1 o3 Models

Search-o1: Agentic Search-Enhanced Large Reasoning Models
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Recommender System LLM-based Architectures

Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems
GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation
Mostly Exploration-Free Algorithms for Contextual Bandits
Deep Interest Network for Click-Through Rate Prediction
Recommending What Video to Watch Next: A Multitask Ranking System
Large Scale Product Graph Construction for Recommendation in E-commerce
Methodologies for Improving Modern Industrial Recommender Systems
Collaborative Filtering Bandits
Collaborative Filtering for Implicit Feedback Datasets
HyperBandit: Contextual Bandit with Hypernetwork for Time-Varying User Preferences in Streaming Recommendation
Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders
Lessons Learnt From Consolidating ML Models in a Large Scale Recommendation System
Wide & Deep Learning for Recommender Systems
KGAT: Knowledge Graph Attention Network for Recommendation
Variational Autoencoders for Collaborative Filtering
Learning Distributed Representations from Reviews for Collaborative Filtering
Deep Neural Networks for YouTube Recommendations
Content-aware Collaborative Music Recommendation Using Pre-trained Neural Networks
Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering
Scalable Neural Contextual Bandit for Recommender Systems
Neural Collaborative Filtering
Neural Collaborative Filtering vs. Matrix Factorization Revisited
Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates
Embarrassingly Shallow Autoencoders for Sparse Data
Unifying Nearest Neighbors Collaborative Filtering
Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model
Learning to Rank for Recommender Systems
Recommender Systems with Social Regularization
Collaborative Filtering with Temporal Dynamics
The Netflix Recommender System: Algorithms, Business Value, and Innovation
Collaborative Deep Learning for Recommender Systems
InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models
Augmenting Netflix Search with In-Session Adapted Recommendations
Tube2Vec: Social and Semantic Embeddings of YouTube Channels
Using Navigation to Improve Recommendations in Real-Time
Monolith: Real Time Recommendation System With Collisionless Embedding Table
Calibrated Recommendations
Dynamically Expandable Graph Convolution for Streaming Recommendation
Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph

Recommenders with Conversational AI

Conversational Recommendation: A Grand AI Challenge
Advances and Challenges in Conversational Recommender Systems: A Survey
Towards Question-based Recommender Systems
Topic-Guided Conversational Recommender in Multiple Domains
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems
A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems
"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems
Large Language Models as Zero-Shot Conversational Recommenders
RevCore: Review-augmented Conversational Recommendation
User-Centric Conversational Recommendation with Multi-Aspect User Modeling
Improving Conversational Recommender Systems via Transformer-based Sequential Modelling
INSPIRED: Toward Sociable Recommendation Dialog Systems
Leveraging Large Language Models in Conversational Recommender Systems

Recommender Systems: General

Curse of “Low” Dimensionality in Recommender Systems
I like it... I like it not: Evaluating User Ratings Noise in Recommender Systems
Posting versus Lurking: Communicating in a Multiple Audience Context
Fast and Slow Learning From Reviews
On Information Distortions in Online Ratings
Why Do People Rate? Theory and Evidence on Online Ratings
Self Selection and Information Role of Online Product Reviews
Measuring the Value of Social Dynamics in Online Product Ratings Forums
Recommendation systems and convergence of online reviews: The type of product network matters!
Cumulated Gain-Based Evaluation of IR Techniques
Reconciling the accuracy-diversity trade-off in recommendations
A Survey on Large Language Models for Recommendation

Recommender Systems: LLMs

Comparing Apples to Apples: Generating Aspect-Aware Comparative Sentences from User Reviews
Large Language Models are Zero-Shot Rankers for Recommender Systems
Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis
GenRec: Large Language Model for Generative Recommendation
Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
On Generative Agents in Recommendation
RecExplainer: Aligning Large Language Models for Recommendation Model Interpretability
CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation
A Multi-facet Paradigm to Bridge Large Language Model and Recommendation

Recommender Systems: Personalized Recommendations

A Personalized Recommender System based-on Knowledge Graph Embeddings
Explainable Recommendation with Personalized Review Retrieval and Aspect Learning
Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)
Review-LLM: Harnessing Large Language Models for Personalized Review Generation
The persuasive effects of political microtargeting in the age of generative artificial intelligence
LLM-Rec: Personalized Recommendation via Prompting Large Language Models
A Probabilistic Model for Using Social Networks in Personalized Item Recommendation
A Contextual-Bandit Approach to Personalized News Article Recommendation
The Architectural Implications of Facebook’s DNN-based Personalized Recommendation
Preference Discerning with LLM-Enhanced Generative Retrieval

Reinforcement Learning and LLMs

External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling
Efficient Reinforcement Learning via Large Language Model-based Search
Reflexion: Language Agents with Verbal Reinforcement Learning
Reward-Robust RLHF in LLMs
Decision Transformer: Reinforcement Learning via Sequence Modeling
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
A Survey of Reinforcement Learning from Human Feedback
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
Reinforcement Learning for Optimizing RAG for Domain Chatbots
LLMs can be Fooled into Labelling a Document as Relevant
Integrating Large Language Models and Reinforcement Learning for Non-Linear Reasoning
Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback

Role play in LLMs

Role-Play with Large Language Models
Role play with large language models
LLMs as Method Actors: A Model for Prompt Engineering and Architecture

Self Refinement in LLMs

Self-Refine: Iterative Refinement with Self-Feedback
Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
RARR: Researching and Revising What Language Models Say, Using Language Models
Fine-grained Hallucination Detection and Editing for Language Models
Rethinking with Retrieval: Faithful Large Language Model Inference
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Self-Evaluation Guided Beam Search for Reasoning
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Self-Rewarding Language Models
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Let’s Verify Step by Step
Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
A Survey on Knowledge Distillation of Large Language Models
Augmenting Autotelic Agents with Large Language Models
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Self-Taught Evaluators
Evaluating Large Language Models at Evaluating Instruction Following
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
Metacognitive Retrieval-Augmented Large Language Models
Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Training Language Models to Self-Correct via Reinforcement Learning
Recursive Introspection: Teaching Language Model Agents How to Self-Improve
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
How to Correctly do Semantic Backpropagation on Language-based Agentic Systems
Boundless Socratic Learning with Language Games
RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

Sentiment and Semantics with LLMs

Artificial intelligence is ineffective and potentially harmful for fact checking
Can Authorship Representation Learning Capture Stylistic Features?
Atesa-bært: A Heterogeneous Ensemble Learning Model For Aspect-based Sentiment Analysis
Classifying YouTube Comments Based on Sentiment and Type of Sentence
Fake News Detectors are Biased against Texts Generated by Large Language Models
HonestBait: Forward References for Attractive but Faithful Headline Generation
Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models
Detoxify Language Model Step-by-Step
Improving Document-Level Sentiment Analysis with User and Product Context
Large Language Models Can Infer Psychological Dispositions Of Social Media Users
Leveraging AI for democratic discourse: Chat interventions can improve online political conversations at scale
Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support
Creativity Has Left the Chat: The Price of Debiasing Language Models
Using Computational Models to Test Syntactic Learnability
Can Large Language Models Transform Computational Social Science?
Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation
A Survey on Lexical Ambiguity Detection and Word Sense Disambiguation
Semantic Specialization for Knowledge-based Word Sense Disambiguation
Large Concept Models: Language Modeling in a Sentence Representation Space

Social Media and Generative AI

Durably reducing conspiracy beliefs through dialogues with AI
Quantifying Controversy on Social Media
SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding
Forecasting the presence and intensity of hostility on Instagram using linguistic and social features
Large Language Models For Social Networks: Applications, Challenges, And Solutions
Attention on the brain

Social Theory and Generative AI

Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
CogBench: a large language model walks into a psychology lab
Should Humans Lie to Machines?  The Incentive Compatibility of Lasso and General Weighted Lasso
Verbal lie detection using Large Language Models
Are Customers Lying to Your Chatbot?
Detecting Deception Using Natural Language Processing and Machine Learning in Datasets on COVID-19 and Climate Change
Truth or lie: Exploring the language of deception
Man vs machine – Detecting deception in online reviews
Transformer-based cynical expression detection in a corpus of Spanish YouTube reviews
Do We Trust ChatGPT as much as Google Search and Wikipedia?
Expanding Explainability: Towards Social Transparency in AI systems
“Hello There! Is Now a Good Time to Talk?”: Opportune Moments for Proactive Interactions with Smart Speakers
Towards Collective Superintelligence, a Pilot Study
People cannot distinguish GPT-4 from a human in a Turing test
Enhancing social cohesion with cooperative bots in societies of greedy, mobile individuals
GPT-4 is judged more human than humans in displaced and inverted Turing tests
The Return of Pseudosciences in Artificial Intelligence: Have Machine Learning and Deep Learning Forgotten Lessons from
Who’s Afraid of (Left) Hyperstitions

Speech and Voice Modes wih Generative AI

Self-Supervised Models of Speech Infer Universal Articulatory Kinematics
POMDP-based Statistical Spoken Dialogue Systems: a Review
LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Synthetic Dialog with LLMs

Self-Directed Synthetic Dialogues and Revisions Technical Report
Suppressing Pink Elephants with Direct Principle Feedback
Synthetic Dialogue Dataset Generation using LLM Agents
DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications
Dynamic Task-Oriented Dialogue: A Comparative Study of Llama-2 and Bert in Slot Value Generation

Tasks and Planning with Generative AI

TaskLAMA: Probing the Complex Task Understanding of Language Models
LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
Large Language Models can accomplish Business Process Management Tasks
Task Contamination: Language Models May Not Be Few-Shot Anymore
Chatbots in Knowledge-Intensive Contexts: Comparing Intent and LLM-Based Systems
Task-Oriented Dialogue with In-Context Learning
Conversational Semantic Parsing for Dialog State Tracking
Task-Oriented Dialogue as Dataflow Synthesis
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
Learning to Map Context-Dependent Sentences to Executable Formal Queries
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
Position: LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
Can Large Language Models Reason and Plan?
Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Can Large Language Models Really Improve by Self-critiquing Their Own Plans?
VAL: Automatic Plan Validation, Continuous Effects and Mixed Initiative Planning using PDDL
TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models
TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation
Real-World Planning with PDDL+ and Beyond
On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs
Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Large Language Models as Planning Domain Generators
Dynamic Planning with a LLM
LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers
Tree Search for Language Model Agents
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts
ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

Test Time Compute with LLMs

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
A Survey on LLM Inference-Time Self-Improvement
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning

Tool Computer Use by LLMs

Agent S: An Open Agentic Framework that Uses Computers Like a Human
Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks
Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling

Training and Fine Tuning Methods

CONTROL PREFIXES for Parameter-Efficient Text Generation
The Curse Of Recursion: Training On Generated Data Makes Models Forget
Language models are weak learners
Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
Extreme Multi-Label Skill Extraction Training using Large Language Models
Exploring Format Consistency for Instruction Tuning
Training language models to follow instructions with human feedback
Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue
Transcendence: Generative Models Can Outperform The Experts That Train Them
Think before you speak: Training Language Models With Pause Tokens
Fine-tuning Language Models for Factuality
Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Supervised Pretraining Can Learn In-Context Reinforcement Learning
Context-PEFT: Efficient Multi-Modal, Multi-Task Fine-Tuning
Instruction Tuning for Large Language Models: A Survey
Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning
Distilling LLMs' Decomposition Abilities into Compact Language Models
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Persistent Pre-Training Poisoning of LLMs
The False Promise of Imitating Proprietary LLMs
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
A Little Human Data Goes A Long Way

Visual and Gui LLMS

OmniParser for Pure Vision Based GUI Agent
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
AutoGLM: Autonomous Foundation Agents for GUIs

Work Applications and Use Cases with LLMs

Social Skill Training with Large Language Models
Generative AI in Real-World Workplaces
Workplace Everyday-Creativity through a Highly-Conversational UI to Large Language Models
Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies

       

©2007 - 2025 by Adrian Chan. All Rights Reserved.