{"total":35,"rows":[{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2406.00755","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","created":"2024-06-02","cited_by_count":45,"area":"lr"},{"id":"2401.06961","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","created":"2024-01-13","cited_by_count":44,"area":"lr"},{"id":"2510.16380","title":"MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes","created":"2025-10-18","cited_by_count":23,"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":"2503.19622","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","created":"2025-03-25","cited_by_count":20,"area":"lr"},{"id":"2506.10979","title":"How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?","created":"2025-06-12","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2507.21476","title":"Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench","created":"2025-07-29","cited_by_count":8,"area":"lr"},{"id":"2601.08258","title":"Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment","created":"2026-01-13","cited_by_count":5,"area":"lr"},{"id":"2412.01621","title":"NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers","created":"2024-12-02","cited_by_count":4,"area":"lr"},{"id":"2401.15030","title":"On the generalization capacity of neural networks during generic multimodal reasoning","created":"2024-01-26","cited_by_count":3,"area":"lr"},{"id":"2406.06588","title":"Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models","created":"2024-06-05","cited_by_count":3,"area":"lr"},{"id":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2505.23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2601.23133","title":"RAudit: A Blind Auditing Protocol for Large Language Model Reasoning","created":"2026-01-30","cited_by_count":2,"area":"lr"},{"id":"2602.08939","title":"CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2603.09957","title":"Think Before You Lie: How Reasoning Leads to Honesty","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2502.12821","title":"Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2601.03263","title":"Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models","created":"2025-12-16","cited_by_count":1,"area":"lr"},{"id":"2606.13262","title":"From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2510.17388","title":"The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2605.09678","title":"Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.31031","title":"GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2607.14099","title":"Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs","created":"2026-05-01","cited_by_count":0,"area":"lr"},{"id":"2607.15313","title":"Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.22128","title":"Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.26113","title":"Differentiable Fuzzy Inference Layer: A Monotone, Compositional Ordinal Reasoning Head for Large Language Models","created":"2026-08-17","cited_by_count":0,"area":"lr"}],"next_cursor":null}