{"list":"other","total":94,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"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":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"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":"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":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"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":"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":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"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":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"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":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"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":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"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":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"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":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"1711.03902","title":"Neural-Symbolic Learning and Reasoning: A Survey and Interpretation","created":"2017-11-10","cited_by_count":196},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135},{"id":"2304.04779","title":"GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner","created":"2023-04-10","cited_by_count":132},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123},{"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":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67},{"id":"2402.13630","title":"UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs","created":"2024-02-21","cited_by_count":66},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64},{"id":"2402.01864","title":"(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice","created":"2024-02-02","cited_by_count":63},{"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":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60},{"id":"2411.01855","title":"Can Language Models Learn to Skip Steps?","created":"2024-11-04","cited_by_count":59},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51},{"id":"2407.01085","title":"Explaining Length Bias in LLM-Based Preference Evaluations","created":"2024-07-01","cited_by_count":49},{"id":"2502.00806","title":"UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs","created":"2025-02-02","cited_by_count":49},{"id":"2405.13873","title":"FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering","created":"2024-05-22","cited_by_count":39},{"id":"2501.06458","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","created":"2025-01-11","cited_by_count":35},{"id":"2502.12206","title":"Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?","created":"2025-02-16","cited_by_count":33},{"id":"2502.04428","title":"Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization","created":"2025-02-06","cited_by_count":29},{"id":"2401.11467","title":"Over-Reasoning and Redundant Calculation of Large Language Models","created":"2024-01-21","cited_by_count":27},{"id":"2410.08085","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering","created":"2024-10-10","cited_by_count":24},{"id":"2502.11451","title":"From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations","created":"2025-02-17","cited_by_count":23},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","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":"2405.00204","title":"General Purpose Verification for Chain of Thought Prompting","created":"2024-04-30","cited_by_count":17},{"id":"2308.01906","title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","created":"2023-08-03","cited_by_count":16},{"id":"2411.15862","title":"Do LLMs Really Think Step-by-step In Implicit Reasoning?","created":"2024-11-24","cited_by_count":16},{"id":"2412.15904","title":"What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning","created":"2024-12-20","cited_by_count":14},{"id":"2407.03953","title":"Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-training","created":"2024-07-04","cited_by_count":7},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4},{"id":"2503.04530","title":"SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning","created":"2025-03-06","cited_by_count":1}],"next_cursor":null}