{"total":77,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2502.09621","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","created":"2025-02-13","cited_by_count":125,"area":"lr"},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2311.07914","title":"Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey","created":"2023-11-14","cited_by_count":92,"area":null},{"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":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70,"area":"wm"},{"id":"2404.05692","title":"Evaluating Mathematical Reasoning Beyond Accuracy","created":"2024-04-08","cited_by_count":69,"area":"lr"},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2503.10621","title":"DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding","created":"2025-03-13","cited_by_count":36,"area":"mllm"},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34,"area":"lr"},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32,"area":"lr"},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29,"area":"lr"},{"id":"2310.00074","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","created":"2023-09-29","cited_by_count":27,"area":"lr"},{"id":"2402.11924","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","created":"2024-02-19","cited_by_count":27,"area":"lr"},{"id":"2503.11557","title":"VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity","created":"2025-03-14","cited_by_count":23,"area":"lr"},{"id":"2502.02362","title":"Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs","created":"2025-02-04","cited_by_count":22,"area":"lr"},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2310.12342","title":"Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking","created":"2023-10-18","cited_by_count":19,"area":"lr"},{"id":"2505.24238","title":"MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM","created":"2025-05-30","cited_by_count":17,"area":"lr"},{"id":"2506.04810","title":"Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2602.09794","title":"Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain","created":"2026-02-10","cited_by_count":17,"area":"lr"},{"id":"2407.00390","title":"Advancing Process Verification for Large Language Models via Tree-Based Preference Learning","created":"2024-06-29","cited_by_count":16,"area":"lr"},{"id":"2402.10528","title":"Can We Verify Step by Step for Incorrect Answer Detection?","created":"2024-02-16","cited_by_count":15,"area":"lr"},{"id":"2506.02126","title":"Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2312.05180","title":"PathFinder: Guided Search over Multi-Step Reasoning Paths","created":"2023-12-08","cited_by_count":12,"area":"lr"},{"id":"2404.03414","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2410.06304","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2305.18170","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","created":"2023-05-29","cited_by_count":11,"area":"lr"},{"id":"2502.06217","title":"Examining False Positives under Inference Scaling for Mathematical Reasoning","created":"2025-02-10","cited_by_count":11,"area":"lr"},{"id":"2402.07214","title":"Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification","created":"2024-02-11","cited_by_count":9,"area":null},{"id":"2502.05675","title":"Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning","created":"2025-02-08","cited_by_count":9,"area":"lr"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2311.17438","title":"CLOMO: Counterfactual Logical Modification with Large Language Models","created":"2023-11-29","cited_by_count":7,"area":"lr"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2503.19193","title":"Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2511.19314","title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking","created":"2025-11-24","cited_by_count":5,"area":"alignment"},{"id":"2603.03332","title":"Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations","created":"2026-02-11","cited_by_count":5,"area":"lr"},{"id":"2311.09613","title":"Digital Socrates: Evaluating LLMs through Explanation Critiques","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2407.01384","title":"Free-text Rationale Generation under Readability Level Control","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2410.12774","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2506.06971","title":"Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2510.08111","title":"Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2506.10467","title":"Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications","created":"2025-06-12","cited_by_count":3,"area":"lr"},{"id":"2509.11026","title":"Rethinking Human Preference Evaluation of LLM Rationales","created":"2025-09-14","cited_by_count":3,"area":"lr"},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.12754","title":"Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2603.07294","title":"MAviS: A Multimodal Conversational Assistant For Avian Species","created":"2026-03-07","cited_by_count":2,"area":"mllm"},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2508.01763","title":"Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2601.10775","title":"LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2602.00564","title":"Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs","created":"2026-01-31","cited_by_count":1,"area":"lr"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2604.12379","title":"Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2604.14121","title":"Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2608.03119","title":"Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2310.12300","title":"Measuring Pointwise $\\mathcal{V}$-Usable Information In-Context-ly","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.13455","title":"Generation of Explanations for Logic Reasoning","created":"2023-11-22","cited_by_count":0,"area":"lr"},{"id":"2509.25844","title":"Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2509.25941","title":"Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2510.11812","title":"PHANTOM RECALL: When Familiar Puzzles Fool Smart Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.13850","title":"Revisiting the UID Hypothesis in LLM Reasoning Traces","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2604.09890","title":"Should We be Pedantic About Reasoning Errors in Machine Translation?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2606.11931","title":"Semantic Grading of Written Answers in Low-Resource Language Bangla Using a Fine-Tuned Lightweight Language Model","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.29278","title":"The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2607.19935","title":"MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.00879","title":"Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.02000","title":"Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.19006","title":"WordPolo: Evaluating Language Models Through Iterative Semantic Feedback","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}