{"list":"other","total":54,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"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":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"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":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2211.09110","title":"Holistic Evaluation of Language Models","created":"2022-11-16","cited_by_count":131},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54},{"id":"2401.11911","title":"Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?","created":"2024-01-22","cited_by_count":48},{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43},{"id":"2508.01191","title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","created":"2025-08-02","cited_by_count":43},{"id":"2504.01005","title":"When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning","created":"2025-04-01","cited_by_count":42},{"id":"2505.13988","title":"The Hallucination Tax of Reinforcement Finetuning","created":"2025-05-20","cited_by_count":40},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38},{"id":"2501.05464","title":"LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models","created":"2024-12-31","cited_by_count":32},{"id":"2503.16212","title":"MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion","created":"2025-03-20","cited_by_count":30},{"id":"2408.14511","title":"Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods","created":"2024-08-25","cited_by_count":29},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27},{"id":"2412.07724","title":"Granite Guardian","created":"2024-12-10","cited_by_count":25},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25},{"id":"2405.06652","title":"Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm","created":"2024-04-06","cited_by_count":23},{"id":"2410.17635","title":"Markov Chain of Thought for Efficient Mathematical Reasoning","created":"2024-10-23","cited_by_count":19},{"id":"2508.14828","title":"Long Chain-of-Thought Reasoning Across Languages","created":"2025-08-20","cited_by_count":19},{"id":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15},{"id":"2310.01290","title":"Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models","created":"2023-10-02","cited_by_count":11},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11},{"id":"2505.10185","title":"The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think","created":"2025-05-15","cited_by_count":9},{"id":"2506.09677","title":"Benchmarking Gaslighting Negation Attacks Against Reasoning Models","created":"2025-06-11","cited_by_count":6},{"id":"2509.24711","title":"Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models","created":"2025-09-29","cited_by_count":4},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3},{"id":"2501.15875","title":"LCTG Bench: LLM Controlled Text Generation Benchmark","created":"2025-01-27","cited_by_count":1}],"next_cursor":null}