{"total":34,"rows":[{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2410.13787","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","created":"2024-10-17","cited_by_count":113,"area":null},{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2310.01846","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","created":"2023-10-03","cited_by_count":44,"area":null},{"id":"2412.20892","title":"Rethinking Aleatoric and Epistemic Uncertainty","created":"2024-12-30","cited_by_count":42,"area":null},{"id":"2405.02079","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2412.18544","title":"Consistency Checks for Language Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2404.15777","title":"A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry","created":"2024-04-24","cited_by_count":17,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2504.13644","title":"Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2507.17951","title":"Are LLM Belief Updates Consistent with Bayes' Theorem?","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2609.33209","title":"Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?","created":"2026-09-27","cited_by_count":6,"area":null},{"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":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2402.01719","title":"Measuring Moral Inconsistencies in Large Language Models","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2406.04752","title":"CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2502.12436","title":"Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2609.02797","title":"Dutch Books for Language Models","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2405.09439","title":"Facilitating Opinion Diversity through Hybrid NLP Approaches","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2504.14039","title":"MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2402.17671","title":"Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2603.10003","title":"Probing the Limits of the Lie Detector Approach to LLM Deception","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2609.33257","title":"Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34864","title":"On the Limits of Metacognitive Monitoring in LLMs","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}