{"list":"other","total":97,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392},{"id":"2109.00110","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","created":"2021-08-31","cited_by_count":391},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2505.23281","title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","created":"2025-05-29","cited_by_count":297},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","created":"2024-05-23","cited_by_count":235},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2302.12433","title":"ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics","created":"2023-02-24","cited_by_count":192},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175},{"id":"2504.16891","title":"AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset","created":"2025-04-23","cited_by_count":174},{"id":"2504.13914","title":"Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":161},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2403.02884","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","created":"2024-03-05","cited_by_count":144},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117},{"id":"2502.12134","title":"SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs","created":"2025-02-17","cited_by_count":116},{"id":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81},{"id":"2408.06450","title":"Evaluating Language Models for Efficient Code Generation","created":"2024-08-12","cited_by_count":73},{"id":"2410.06526","title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks","created":"2024-10-09","cited_by_count":70},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64},{"id":"2401.05618","title":"The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models","created":"2024-01-11","cited_by_count":63},{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58},{"id":"2503.19633","title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","created":"2025-03-25","cited_by_count":49},{"id":"2506.02536","title":"Answer Convergence as a Signal for Early Stopping in Reasoning","created":"2025-06-03","cited_by_count":40},{"id":"2504.03234","title":"Think When You Need: Self-Adaptive Chain-of-Thought Learning","created":"2025-04-04","cited_by_count":38},{"id":"2504.18458","title":"Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning","created":"2025-04-25","cited_by_count":36},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34},{"id":"2504.21659","title":"Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization","created":"2025-04-30","cited_by_count":33},{"id":"2501.01306","title":"Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking","created":"2025-01-02","cited_by_count":31},{"id":"2504.13941","title":"Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning","created":"2025-04-15","cited_by_count":31},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30},{"id":"2501.14275","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","created":"2025-01-24","cited_by_count":29},{"id":"2505.08311","title":"AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale","created":"2025-05-13","cited_by_count":29},{"id":"2505.14810","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","created":"2025-05-20","cited_by_count":28},{"id":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27},{"id":"2502.12202","title":"To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models","created":"2025-02-16","cited_by_count":22},{"id":"2505.22148","title":"What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning","created":"2025-05-28","cited_by_count":21},{"id":"2409.08561","title":"Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding","created":"2024-09-13","cited_by_count":19},{"id":"2502.08482","title":"Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning","created":"2025-02-12","cited_by_count":19},{"id":"2505.11225","title":"HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization","created":"2025-05-16","cited_by_count":19},{"id":"2504.17565","title":"DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training","created":"2025-04-24","cited_by_count":18},{"id":"2505.15404","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","created":"2025-05-21","cited_by_count":18},{"id":"2503.12918","title":"ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs","created":"2025-03-17","cited_by_count":16},{"id":"2504.20708","title":"Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think","created":"2025-04-29","cited_by_count":16},{"id":"2505.10425","title":"Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs","created":"2025-05-15","cited_by_count":16},{"id":"2505.02156","title":"Adaptive Social Learning via Mode Policy Optimization for Language Agents","created":"2025-05-04","cited_by_count":15},{"id":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","cited_by_count":15},{"id":"2505.10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","created":"2025-05-16","cited_by_count":14},{"id":"2409.17433","title":"HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows","created":"2024-09-25","cited_by_count":13},{"id":"2506.04182","title":"Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models","created":"2025-06-04","cited_by_count":8},{"id":"2505.19756","title":"Efficient Reasoning via Chain of Unconscious Thought","created":"2025-05-26","cited_by_count":7},{"id":"2503.01923","title":"Output Length Effect on DeepSeek-R1's Safety in Forced Thinking","created":"2025-03-02","cited_by_count":6},{"id":"2507.00606","title":"Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies","created":"2025-07-01","cited_by_count":3}],"next_cursor":null}