{"total":47,"rows":[{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2305.16867","title":"Playing repeated games with Large Language Models","created":"2023-05-26","cited_by_count":217,"area":null},{"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":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"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":"2309.15129","title":"Evaluating Cognitive Maps and Planning in Large Language Models with CogEval","created":"2023-09-25","cited_by_count":77,"area":null},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"id":"2307.09042","title":"Emotional Intelligence of Large Language Models","created":"2023-07-18","cited_by_count":58,"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":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44,"area":null},{"id":"2306.07075","title":"Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2308.11764","title":"Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2308.02575","title":"Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings","created":"2023-08-03","cited_by_count":34,"area":null},{"id":"2310.11158","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","created":"2023-10-17","cited_by_count":33,"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":"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":"2502.21098","title":"Re-evaluating Theory of Mind evaluation in large language models","created":"2025-02-28","cited_by_count":23,"area":null},{"id":"2403.06769","title":"Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation","created":"2024-03-11","cited_by_count":21,"area":null},{"id":"2310.19671","title":"Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding","created":"2023-10-30","cited_by_count":20,"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":"2310.05976","title":"An evolutionary model of personality traits related to cooperative behavior using a large language model","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2408.14307","title":"LLM-3D Print: Large Language Models To Monitor and Control 3D Printing","created":"2024-08-26","cited_by_count":18,"area":null},{"id":"2305.14020","title":"Does ChatGPT have Theory of Mind?","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2412.08414","title":"Detecting Conversational Mental Manipulation with Intent-Aware Prompting","created":"2024-12-11","cited_by_count":16,"area":null},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2309.04019","title":"Evaluation of large language models for discovery of gene set function","created":"2023-09-07","cited_by_count":14,"area":null},{"id":"2307.02792","title":"What Should Data Science Education Do with Large Language Models?","created":"2023-07-06","cited_by_count":13,"area":null},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","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":"2307.05082","title":"OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2401.08438","title":"CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models","created":"2024-01-06","cited_by_count":6,"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":"2310.06983","title":"Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models","created":"2023-10-10","cited_by_count":4,"area":null},{"id":"2403.09740","title":"Teaching Machines to Code: Smart Contract Translation with LLMs","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2503.16468","title":"Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2506.09450","title":"UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2305.14740","title":"ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2410.08545","title":"Humanity in AI: Detecting the Personality of Large Language Models","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2601.08342","title":"Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2602.12150","title":"GPT-4o Lacks Core Features of Theory of Mind","created":"2026-02-12","cited_by_count":1,"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":"2608.26291","title":"Assessing mentalization in humans and large language models","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2410.12959","title":"Large Language Models as a Tool for Mining Object Knowledge","created":"2024-10-16","cited_by_count":0,"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":"2603.04161","title":"Traces of Social Competence in Large Language Models","created":"2026-03-04","cited_by_count":0,"area":null}],"next_cursor":null}