{"total":57,"rows":[{"id":"2504.18412","title":"Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers","created":"2025-04-25","cited_by_count":69,"area":null},{"id":"2505.00026","title":"Theory of Mind in Large Language Models: Assessment and Enhancement","created":"2025-04-26","cited_by_count":25,"area":null},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17,"area":null},{"id":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"area":null},{"id":"2504.10839","title":"Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective","created":"2025-04-15","cited_by_count":14,"area":"lr"},{"id":"2505.18943","title":"MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems","created":"2025-05-25","cited_by_count":13,"area":"lr"},{"id":"2502.14359","title":"Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2502.17701","title":"From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2507.16196","title":"Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2502.21297","title":"Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind","created":"2025-02-28","cited_by_count":8,"area":null},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2606.08878","title":"PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting","created":"2026-06-07","cited_by_count":6,"area":"agents"},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2509.05066","title":"ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2509.17054","title":"TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?","created":"2025-09-21","cited_by_count":5,"area":null},{"id":"2603.09249","title":"Social-R1: Towards Human-like Social Reasoning in LLMs","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2601.15628","title":"CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2602.16085","title":"Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs","created":"2026-02-17","cited_by_count":3,"area":"lr"},{"id":"2605.09826","title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2603.26089","title":"Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.20443","title":"DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2607.03598","title":"They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2506.17352","title":"Towards Safety Evaluations of Theory of Mind in Large Language Models","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2602.10298","title":"On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models","created":"2026-02-10","cited_by_count":1,"area":"wm"},{"id":"2604.11666","title":"Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2606.03471","title":"A formal definition and meta-model for a machine theory of mind","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.04184","title":"GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs","created":"2026-06-02","cited_by_count":1,"area":"wm"},{"id":"2606.31916","title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2609.01352","title":"CHARM: Character Hallucination for Multicultural Role Play Benchmark","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.15972","title":"Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2505.17249","title":"Where You Go is Who You Are: Behavioral Theory-Guided LLMs for Inverse Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2505.24500","title":"TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.14803","title":"OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2510.02660","title":"When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.08743","title":"Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence","created":"2025-12-09","cited_by_count":0,"area":"agents"},{"id":"2512.19992","title":"S$^3$IT: A Benchmark for Spatially Situated Social Intelligence Test","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.12410","title":"Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimation","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2603.28925","title":"Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.02315","title":"Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.05273","title":"Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.02475","title":"Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives","created":"2026-05-04","cited_by_count":0,"area":"wm"},{"id":"2605.07823","title":"SCENE: Recognizing Social Norms and Sanctioning in Group Chats","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.14600","title":"LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.11363","title":"Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.11696","title":"Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2607.28648","title":"Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2608.20763","title":"CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2609.04384","title":"You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.15163","title":"Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16895","title":"Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17327","title":"The Curse of Knowledge in Role-Playing Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18610","title":"Jev-ToM: Evaluating Theory of Mind in Typed Decision Models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19796","title":"Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}