{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156},{"id":"2409.18486","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","created":"2024-09-27","cited_by_count":127},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"2503.01141","title":"How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach","created":"2025-03-03","cited_by_count":97},{"id":"2503.04761","title":"Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations","created":"2025-02-11","cited_by_count":96},{"id":"2406.12334","title":"What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering","created":"2024-06-18","cited_by_count":90},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85},{"id":"2506.08343","title":"Wait, We Don't Need to \"Wait\"! Removing Thinking Tokens Improves Reasoning Efficiency","created":"2025-06-10","cited_by_count":66},{"id":"2504.07139","title":"Artificial Intelligence Index Report 2025","created":"2025-04-08","cited_by_count":64},{"id":"2509.09677","title":"The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs","created":"2025-09-11","cited_by_count":64},{"id":"2502.04313","title":"Great Models Think Alike and this Undermines AI Oversight","created":"2025-02-06","cited_by_count":58},{"id":"2305.06566","title":"ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models","created":"2023-05-11","cited_by_count":54},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50},{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41},{"id":"2502.11544","title":"Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis","created":"2025-02-17","cited_by_count":26},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25},{"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":"2501.19383","title":"Decoding-based Regression","created":"2025-01-31","cited_by_count":12},{"id":"2403.03424","title":"Generative News Recommendation","created":"2024-03-06","cited_by_count":10},{"id":"2503.07329","title":"Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models","created":"2025-03-10","cited_by_count":10},{"id":"2511.08789","title":"A Generalized Bias-Variance Decomposition for Bregman Divergences","created":"2025-11-11","cited_by_count":8},{"id":"2505.17225","title":"Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models","created":"2025-05-22","cited_by_count":6},{"id":"2502.15850","title":"Forecasting Frontier Language Model Agent Capabilities","created":"2025-02-21","cited_by_count":5},{"id":"2405.13007","title":"News Recommendation with Category Description by a Large Language Model","created":"2024-05-13","cited_by_count":4},{"id":"2509.15510","title":"The (Short-Term) Effects of Large Language Models on Unemployment and Earnings","created":"2025-09-19","cited_by_count":1}],"next_cursor":null}