{"list":"other","total":55,"rows":[{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"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":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"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},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2401.05856","title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","created":"2024-01-11","cited_by_count":139},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110},{"id":"2504.05506","title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","created":"2025-04-07","cited_by_count":108},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58},{"id":"1905.07374","title":"Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs","created":"2019-05-17","cited_by_count":53},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41},{"id":"2004.12704","title":"Semantic Graphs for Generating Deep Questions","created":"2020-04-27","cited_by_count":38},{"id":"2405.02079","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","created":"2024-05-03","cited_by_count":36},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35},{"id":"2309.08503","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","created":"2023-09-15","cited_by_count":35},{"id":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31},{"id":"2411.05345","title":"Reasoning Robustness of LLMs to Adversarial Typographical Errors","created":"2024-11-08","cited_by_count":31},{"id":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","cited_by_count":26},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26},{"id":"2401.09395","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","created":"2024-01-17","cited_by_count":20},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20},{"id":"2305.03598","title":"NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports","created":"2023-05-05","cited_by_count":18},{"id":"2405.04793","title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","created":"2024-05-08","cited_by_count":18},{"id":"2403.02698","title":"Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment","created":"2024-03-05","cited_by_count":17},{"id":"2407.02352","title":"Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification","created":"2024-07-02","cited_by_count":17},{"id":"2502.14765","title":"Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning","created":"2025-02-20","cited_by_count":17},{"id":"2506.15569","title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","created":"2025-06-18","cited_by_count":17},{"id":"2106.01191","title":"Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verification","created":"2021-06-02","cited_by_count":16},{"id":"2503.15354","title":"Optimizing Decomposition for Optimal Claim Verification","created":"2025-03-19","cited_by_count":10},{"id":"2506.12301","title":"Unveiling Confirmation Bias in Chain-of-Thought Reasoning","created":"2025-06-14","cited_by_count":10},{"id":"2405.00708","title":"Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis","created":"2024-04-23","cited_by_count":8},{"id":"2506.04585","title":"MuSciClaims: Multimodal Scientific Claim Verification","created":"2025-06-05","cited_by_count":8},{"id":"2502.10003","title":"SciClaimHunt: A Large Dataset for Evidence-based Scientific Claim Verification","created":"2025-02-14","cited_by_count":4},{"id":"2506.09148","title":"Adversarial Text Generation with Dynamic Contextual Perturbation","created":"2025-06-10","cited_by_count":2}],"next_cursor":null}