{"total":44,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789,"area":"lr"},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316,"area":"lr"},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128,"area":"lr"},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2305.13412","title":"Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method","created":"2023-05-22","cited_by_count":76,"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":"2311.09702","title":"Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?","created":"2023-11-16","cited_by_count":26,"area":"lr"},{"id":"2507.02778","title":"Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models","created":"2025-07-03","cited_by_count":20,"area":"lr"},{"id":"2410.05801","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2509.25177","title":"Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2308.15118","title":"Large Language Models on the Chessboard: A Study on ChatGPT's Formal Language Comprehension and Complex Reasoning Skills","created":"2023-08-29","cited_by_count":9,"area":"lr"},{"id":"2309.16436","title":"Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving","created":"2023-09-28","cited_by_count":6,"area":"lr"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2607.22962","title":"ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control","created":"2026-07-25","cited_by_count":6,"area":"lr"},{"id":"2205.10442","title":"Down and Across: Introducing Crossword-Solving as a New NLP Benchmark","created":"2022-05-20","cited_by_count":4,"area":"lr"},{"id":"2410.10584","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","created":"2024-10-14","cited_by_count":4,"area":"lr"},{"id":"2404.09868","title":"Software Engineering Methods For AI-Driven Deductive Legal Reasoning","created":"2024-04-15","cited_by_count":3,"area":"lr"},{"id":"2511.05747","title":"CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization","created":"2025-11-07","cited_by_count":3,"area":"lr"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2603.03640","title":"MistyPilot: An Agentic Fast-Slow Thinking LLM Framework for Misty Social Robots","created":"2026-03-04","cited_by_count":3,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2408.12333","title":"GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness Reasoning","created":"2024-08-22","cited_by_count":1,"area":"lr"},{"id":"2509.10753","title":"HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2510.09106","title":"When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2511.12520","title":"TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction","created":"2025-11-16","cited_by_count":1,"area":"lr"},{"id":"2601.02739","title":"Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.04086","title":"KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2604.06505","title":"MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.25809","title":"Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2601.22312","title":"SCALAR: Quantifying Structural Hallucination, Consistency, and Reasoning Gaps in Materials Foundation Models","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.02427","title":"Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.22367","title":"Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window","created":"2026-03-23","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":"2605.16675","title":"LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning","created":"2026-05-15","cited_by_count":0,"area":"lr"},{"id":"2606.13171","title":"NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.18249","title":"MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}