{"list":"other","total":52,"rows":[{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2502.01100","title":"ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning","created":"2025-02-03","cited_by_count":201},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152},{"id":"2306.05836","title":"Can Large Language Models Infer Causation from Correlation?","created":"2023-06-09","cited_by_count":146},{"id":"2502.05167","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","created":"2025-02-07","cited_by_count":126},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120},{"id":"2308.13149","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","created":"2023-08-25","cited_by_count":115},{"id":"2407.01725","title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","created":"2024-07-01","cited_by_count":109},{"id":"2312.04350","title":"CLadder: Assessing Causal Reasoning in Language Models","created":"2023-12-07","cited_by_count":107},{"id":"2405.18357","title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","created":"2024-05-28","cited_by_count":100},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89},{"id":"2005.02259","title":"Learning programs by learning from failures","created":"2020-05-05","cited_by_count":73},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72},{"id":"2504.10415","title":"LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models","created":"2025-04-14","cited_by_count":71},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70},{"id":"2410.06526","title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks","created":"2024-10-09","cited_by_count":70},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51},{"id":"2505.14615","title":"SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas","created":"2025-05-20","cited_by_count":33},{"id":"2604.15149","title":"LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking","created":"2026-04-16","cited_by_count":28},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","cited_by_count":27},{"id":"2501.14851","title":"JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models","created":"2025-01-24","cited_by_count":22},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","cited_by_count":18},{"id":"2203.12186","title":"AbductionRules: Training Transformers to Explain Unexpected Inputs","created":"2022-03-23","cited_by_count":17},{"id":"2406.12066","title":"Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks","created":"2024-06-17","cited_by_count":17},{"id":"2502.12616","title":"Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions","created":"2025-02-18","cited_by_count":17},{"id":"2506.04810","title":"Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study","created":"2025-06-05","cited_by_count":17},{"id":"2410.14399","title":"SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning","created":"2024-10-18","cited_by_count":9},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7},{"id":"2510.06774","title":"Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition","created":"2025-10-08","cited_by_count":7},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6},{"id":"2601.21210","title":"Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification","created":"2026-01-29","cited_by_count":5},{"id":"2509.16226","title":"On LLM-Based Scientific Inductive Reasoning Beyond Equations","created":"2025-09-12","cited_by_count":2}],"next_cursor":null}