{"total":15,"rows":[{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104,"area":"lr"},{"id":"2308.15399","title":"Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?","created":"2023-08-29","cited_by_count":36,"area":"lr"},{"id":"2501.16513","title":"Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models","created":"2025-01-27","cited_by_count":16,"area":"lr"},{"id":"2402.09404","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","created":"2024-02-14","cited_by_count":8,"area":"lr"},{"id":"2405.12933","title":"Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs","created":"2024-05-21","cited_by_count":8,"area":"lr"},{"id":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2605.14537","title":"Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2408.04648","title":"PLUGH: A Benchmark for Spatial Understanding and Reasoning in Large Language Models","created":"2024-08-03","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2603.16017","title":"Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2603.21006","title":"How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2604.22119","title":"Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2608.08061","title":"CORDA: A Benchmark for Hierarchical Harm-Centric Moral Reasoning in Large Language Models","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.05088","title":"Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?","created":"2026-09-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}