{"list":"other","total":62,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2310.01061","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","created":"2023-10-02","cited_by_count":328},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122},{"id":"1811.10971","title":"The Fact Extraction and VERification (FEVER) Shared Task","created":"2018-11-27","cited_by_count":108},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"2106.09248","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","created":"2021-06-17","cited_by_count":91},{"id":"2304.14732","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","created":"2023-04-28","cited_by_count":73},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64},{"id":"1802.03052","title":"WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference","created":"2018-02-08","cited_by_count":60},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48},{"id":"2305.13252","title":"\"According to ...\": Prompting Language Models Improves Quoting from Pre-Training Data","created":"2023-05-22","cited_by_count":42},{"id":"2403.11903","title":"A Closer Look at Claim Decomposition","created":"2024-03-18","cited_by_count":41},{"id":"1909.03042","title":"Uncertain Natural Language Inference","created":"2019-09-06","cited_by_count":35},{"id":"2010.03001","title":"A Review on Fact Extraction and Verification","created":"2020-10-06","cited_by_count":29},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29},{"id":"2402.14897","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","created":"2024-02-22","cited_by_count":28},{"id":"2406.12830","title":"What Are the Odds? Language Models Are Capable of Probabilistic Reasoning","created":"2024-06-18","cited_by_count":26},{"id":"2402.06025","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","created":"2024-02-08","cited_by_count":24},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24},{"id":"2210.01293","title":"ThinkSum: Probabilistic reasoning over sets using large language models","created":"2022-10-04","cited_by_count":23},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20},{"id":"2309.07694","title":"Tree of Uncertain Thoughts Reasoning for Large Language Models","created":"2023-09-14","cited_by_count":19},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19},{"id":"2404.12494","title":"BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models","created":"2024-04-18","cited_by_count":18},{"id":"2502.14634","title":"CER: Confidence Enhanced Reasoning in LLMs","created":"2025-02-20","cited_by_count":17},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16},{"id":"2402.04978","title":"An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration","created":"2024-02-07","cited_by_count":16},{"id":"2405.21028","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","created":"2024-05-31","cited_by_count":15},{"id":"2210.03102","title":"Ambiguous Images With Human Judgments for Robust Visual Event Classification","created":"2022-10-06","cited_by_count":12},{"id":"2402.14798","title":"Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic","created":"2024-02-22","cited_by_count":12},{"id":"2402.19467","title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","created":"2024-02-29","cited_by_count":12},{"id":"2403.09724","title":"ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs","created":"2024-03-12","cited_by_count":11},{"id":"2502.08080","title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","created":"2025-02-12","cited_by_count":11},{"id":"2402.14268","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","created":"2024-02-22","cited_by_count":9},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7},{"id":"2404.15588","title":"Minimal Evidence Group Identification for Claim Verification","created":"2024-04-24","cited_by_count":5},{"id":"2406.09458","title":"Updating CLIP to Prefer Descriptions Over Captions","created":"2024-06-12","cited_by_count":3}],"next_cursor":null}