{"total":172,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201,"area":"lr"},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99,"area":"lr"},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2311.10227","title":"Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities","created":"2023-11-16","cited_by_count":89,"area":"wm"},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2401.06866","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","created":"2024-01-12","cited_by_count":66,"area":null},{"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":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58,"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":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2406.17055","title":"Large Language Models Assume People are More Rational than We Really are","created":"2024-06-24","cited_by_count":54,"area":null},{"id":"2404.13627","title":"NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding","created":"2024-04-21","cited_by_count":51,"area":null},{"id":"2408.12574","title":"MuMA-ToM: Multi-modal Multi-Agent Theory of Mind","created":"2024-08-22","cited_by_count":51,"area":"agents"},{"id":"2407.07086","title":"Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models","created":"2024-07-09","cited_by_count":48,"area":"agents"},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2311.16093","title":"Visual cognition in multimodal large language models","created":"2023-11-27","cited_by_count":38,"area":"mllm"},{"id":"2504.19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects","created":"2025-04-28","cited_by_count":32,"area":"agents"},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30,"area":"lr"},{"id":"2502.11881","title":"Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"area":null},{"id":"2406.12203","title":"InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context","created":"2024-06-18","cited_by_count":26,"area":null},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"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":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2502.15676","title":"AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling","created":"2025-02-21","cited_by_count":23,"area":"agents"},{"id":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2407.06004","title":"Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models","created":"2024-07-08","cited_by_count":22,"area":null},{"id":"2407.01455","title":"TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind","created":"2024-07-01","cited_by_count":21,"area":null},{"id":"2509.10127","title":"Population-Aligned Persona Generation for LLM-based Social Simulation","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2505.17663","title":"Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2501.09056","title":"Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition","created":"2025-01-15","cited_by_count":17,"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":"2408.08978","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2402.11051","title":"Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives","created":"2024-02-16","cited_by_count":14,"area":null},{"id":"2406.05343","title":"M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark","created":"2024-06-08","cited_by_count":14,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2409.11733","title":"Human-like Affective Cognition in Foundation Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2410.16676","title":"CausalEval: Towards Better Causal Reasoning in Language Models","created":"2024-10-22","cited_by_count":13,"area":"lr"},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2411.02478","title":"Imagining and building wise machines: The centrality of AI metacognition","created":"2024-11-04","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":"2503.22152","title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos","created":"2025-03-28","cited_by_count":12,"area":"lr"},{"id":"2503.04730","title":"WinClick: GUI Grounding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":11,"area":null},{"id":"2510.04764","title":"Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models","created":"2025-10-06","cited_by_count":11,"area":null},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2509.22856","title":"The Bias is in the Details: An Assessment of Cognitive Bias in LLMs","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2409.13354","title":"Recent Advancement of Emotion Cognition in Large Language Models","created":"2024-09-20","cited_by_count":9,"area":null},{"id":"2412.13631","title":"Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning","created":"2024-12-18","cited_by_count":9,"area":"lr"},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2506.13331","title":"Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization","created":"2025-06-16","cited_by_count":9,"area":"lr"},{"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":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9,"area":null},{"id":"2406.17513","title":"Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models","created":"2024-06-25","cited_by_count":8,"area":null},{"id":"2501.01705","title":"The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters","created":"2025-01-03","cited_by_count":8,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2503.17485","title":"SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia","created":"2025-03-21","cited_by_count":8,"area":null},{"id":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2507.08892","title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2406.14737","title":"Dissecting the Ullman Variations with a SCALPEL: Why do LLMs fail at Trivial Alterations to the False Belief Task?","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2608.12307","title":"AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses","created":"2026-08-12","cited_by_count":7,"area":"distill"},{"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":"2503.03340","title":"EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States","created":"2025-03-05","cited_by_count":6,"area":"lr"},{"id":"2503.11227","title":"GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction","created":"2025-03-14","cited_by_count":6,"area":null},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2606.08878","title":"PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting","created":"2026-06-07","cited_by_count":6,"area":"agents"},{"id":"2402.02547","title":"Integration of cognitive tasks into artificial general intelligence test for large models","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"id":"2408.14419","title":"CHARTOM: A Visual Theory-of-Mind Benchmark for LLMs on Misleading Charts","created":"2024-08-26","cited_by_count":5,"area":"mllm"},{"id":"2410.01926","title":"MARPLE: A Benchmark for Long-Horizon Inference","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2411.00038","title":"Topic-Conversation Relevance (TCR) Dataset and Benchmarks","created":"2024-10-29","cited_by_count":5,"area":null},{"id":"2411.12977","title":"MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning","created":"2024-11-20","cited_by_count":5,"area":"agents"},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","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":"2511.23055","title":"MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents","created":"2025-11-28","cited_by_count":5,"area":"agents"},{"id":"2404.00938","title":"How Can Large Language Models Enable Better Socially Assistive Human-Robot Interaction: A Brief Survey","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2404.10975","title":"Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models","created":"2024-04-17","cited_by_count":4,"area":"lr"},{"id":"2406.10265","title":"Improving Language Models for Emotion Analysis: Insights from Cognitive Science","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2507.03682","title":"Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2509.03867","title":"Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth","created":"2025-09-04","cited_by_count":4,"area":null},{"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":"2604.18982","title":"SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2312.03042","title":"Inherent limitations of LLMs regarding spatial information","created":"2023-12-05","cited_by_count":3,"area":null},{"id":"2506.01512","title":"Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2508.12480","title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2509.17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture","created":"2025-09-21","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":"2403.11366","title":"JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning","created":"2024-03-17","cited_by_count":2,"area":"rag"},{"id":"2503.15491","title":"Agreeing to Interact in Human-Robot Interaction using Large Language Models and Vision Language Models","created":"2025-01-07","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}