{"total":20,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2410.12311","title":"Open Domain Question Answering with Conflicting Contexts","created":"2024-10-16","cited_by_count":18,"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":"2308.15299","title":"TaskLAMA: Probing the Complex Task Understanding of Language Models","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2510.06475","title":"PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2311.06697","title":"Trusted Source Alignment in Large Language Models","created":"2023-11-12","cited_by_count":4,"area":null},{"id":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2412.16232","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","created":"2024-12-19","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":"2606.23196","title":"When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2607.18232","title":"It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2505.17345","title":"The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2510.11812","title":"PHANTOM RECALL: When Familiar Puzzles Fool Smart Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2603.22735","title":"Explanation Generation for Contradiction Reconciliation with LLMs","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2609.38621","title":"When Scientific Contradictions Are Lost in Translation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18579","title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}