{"total":32,"rows":[{"id":"2405.18870","title":"LLMs achieve adult human performance on higher-order theory of mind tasks","created":"2024-05-29","cited_by_count":61,"area":null},{"id":"2410.13648","title":"SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2502.21098","title":"Re-evaluating Theory of Mind evaluation in large language models","created":"2025-02-28","cited_by_count":23,"area":null},{"id":"2504.09689","title":"EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety","created":"2025-04-13","cited_by_count":21,"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":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2505.22961","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","created":"2025-05-29","cited_by_count":12,"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":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2410.21195","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2504.12805","title":"Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation","created":"2025-04-17","cited_by_count":3,"area":null},{"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":"2605.26322","title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","created":"2026-05-25","cited_by_count":2,"area":null},{"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":"2504.04238","title":"Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2505.12651","title":"$\\texttt{DIAMONDs}$: A Dataset for $\\mathbb{D}$ynamic $\\mathbb{I}$nformation $\\mathbb{A}$nd $\\mathbb{M}$ental modeling $\\mathbb{O}$f $\\mathbb{N}$umeric $\\mathbb{D}$iscussions","created":"2025-05-19","cited_by_count":0,"area":null},{"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":"2511.00261","title":"Spot The Ball: A Benchmark for Visual Social Inference","created":"2025-10-31","cited_by_count":0,"area":null},{"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":"2603.14646","title":"Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.07823","title":"SCENE: Recognizing Social Norms and Sanctioning in Group Chats","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.01063","title":"MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention","created":"2026-05-31","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":"2606.30989","title":"Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG","created":"2026-06-30","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":"2607.11945","title":"Belief-reality separation lives in routing over a shared value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.35409","title":"AwarenessBench: Assessing Cognitive Capabilities of Language Models","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}