{"total":26,"rows":[{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94,"area":"lr"},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62,"area":"lr"},{"id":"2505.12864","title":"LEXam: Benchmarking Legal Reasoning on 340 Law Exams","created":"2025-05-19","cited_by_count":54,"area":"lr"},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20,"area":"lr"},{"id":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2602.13294","title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2401.05190","title":"DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs","created":"2024-01-10","cited_by_count":5,"area":"lr"},{"id":"2406.18925","title":"Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding","created":"2024-06-27","cited_by_count":3,"area":"lr"},{"id":"2604.04944","title":"Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space","created":"2026-03-15","cited_by_count":3,"area":"lr"},{"id":"2606.23595","title":"SPIRAL: Learning to Search and Aggregate","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2501.13833","title":"On the Reasoning Capacity of AI Models and How to Quantify It","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2504.10090","title":"CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography","created":"2025-04-14","cited_by_count":2,"area":"lr"},{"id":"2509.21284","title":"Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.29025","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2603.22730","title":"How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Kr\\\"ugel, and Uhl (2025)","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2604.10034","title":"AI Achieves a Perfect LSAT Score","created":"2026-04-11","cited_by_count":0,"area":"lr"},{"id":"2606.15589","title":"Is Code Better Than Language for Algorithmic Reasoning","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2608.15445","title":"Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2608.26161","title":"Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models","created":"2026-07-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}