{"total":64,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292,"area":null},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230,"area":null},{"id":"2302.02083","title":"Evaluating Large Language Models in Theory of Mind Tasks","created":"2023-02-04","cited_by_count":222,"area":"wm"},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220,"area":"wm"},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171,"area":null},{"id":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2310.03051","title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","created":"2023-10-04","cited_by_count":76,"area":"agents"},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70,"area":null},{"id":"2310.16755","title":"HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models","created":"2023-10-25","cited_by_count":63,"area":"lr"},{"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":"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":"2310.20320","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","created":"2023-10-31","cited_by_count":48,"area":null},{"id":"2107.05697","title":"Few-shot Language Coordination by Modeling Theory of Mind","created":"2021-07-12","cited_by_count":32,"area":null},{"id":"2310.19619","title":"Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models","created":"2023-10-30","cited_by_count":32,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2305.15068","title":"ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind","created":"2023-05-24","cited_by_count":28,"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":"2505.00026","title":"Theory of Mind in Large Language Models: Assessment and Enhancement","created":"2025-04-26","cited_by_count":25,"area":null},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22,"area":null},{"id":"2212.10060","title":"I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21,"area":"lr"},{"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":"2409.20222","title":"Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2211.04684","title":"Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind","created":"2022-11-09","cited_by_count":19,"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":"2305.03353","title":"MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"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":"2306.09299","title":"Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization","created":"2023-06-15","cited_by_count":16,"area":"agents"},{"id":"2303.01502","title":"Computational Language Acquisition with Theory of Mind","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2310.08102","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","created":"2023-10-12","cited_by_count":15,"area":null},{"id":"2403.02451","title":"Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground","created":"2024-03-04","cited_by_count":10,"area":null},{"id":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2305.11271","title":"Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue","created":"2023-05-18","cited_by_count":9,"area":null},{"id":"2406.13763","title":"Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"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":"2301.05149","title":"Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2411.01562","title":"Are LLMs good pragmatic speakers?","created":"2024-11-03","cited_by_count":7,"area":null},{"id":"2301.06926","title":"Memory-Augmented Theory of Mind Network","created":"2023-01-17","cited_by_count":6,"area":null},{"id":"2403.16517","title":"Norm Violation Detection in Multi-Agent Systems using Large Language Models: A Pilot Study","created":"2024-03-25","cited_by_count":6,"area":"agents"},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2402.07402","title":"BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind","created":"2024-02-12","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":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"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":"2309.10744","title":"Evaluating Large Language Models' Ability Using a Psychiatric Screening Tool Based on Metaphor and Sarcasm Scenarios","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2409.17458","title":"RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking","created":"2024-09-26","cited_by_count":2,"area":"safety"},{"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":"2306.15253","title":"MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2112.15360","title":"Making AI 'Smart': Bridging AI and Cognitive Science","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2506.13641","title":"EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2509.11868","title":"Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models","created":"2025-09-15","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":"2601.01878","title":"Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs","created":"2026-01-05","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":"2601.13687","title":"Understanding Mental States to Guide Social Influence in Multi-Person Group Dialogue","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.04161","title":"Traces of Social Competence in Large Language Models","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.24484","title":"Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models","created":"2026-03-25","cited_by_count":0,"area":"mllm"}],"next_cursor":null}