{"list":"other","total":91,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"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":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2504.03160","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","created":"2025-04-04","cited_by_count":286},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222},{"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":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"1705.00106","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","created":"2017-04-29","cited_by_count":186},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"1907.06554","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","created":"2019-07-15","cited_by_count":139},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43},{"id":"2402.03289","title":"Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS","created":"2024-02-05","cited_by_count":43},{"id":"2410.23856","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","created":"2024-10-31","cited_by_count":41},{"id":"2410.05318","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","created":"2024-10-05","cited_by_count":40},{"id":"2402.11199","title":"Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs","created":"2024-02-17","cited_by_count":32},{"id":"2406.00806","title":"Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection","created":"2024-06-02","cited_by_count":32},{"id":"2410.03131","title":"Code Comprehension then Auditing for Unsupervised LLM Evaluation","created":"2024-10-04","cited_by_count":32},{"id":"2410.02828","title":"PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System","created":"2024-10-01","cited_by_count":31},{"id":"1805.04843","title":"Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders","created":"2018-05-13","cited_by_count":26},{"id":"2501.10799","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback","created":"2025-01-18","cited_by_count":22},{"id":"2307.05131","title":"Overview of BioASQ 2023: The eleventh BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering","created":"2023-07-11","cited_by_count":18},{"id":"2306.09104","title":"On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation","created":"2023-06-15","cited_by_count":16},{"id":"2410.08048","title":"VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers","created":"2024-10-10","cited_by_count":14},{"id":"2311.01276","title":"Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel","created":"2023-11-02","cited_by_count":10},{"id":"2311.01196","title":"Combating Bilateral Edge Noise for Robust Link Prediction","created":"2023-11-02","cited_by_count":9},{"id":"2412.09666","title":"Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic","created":"2024-12-12","cited_by_count":3}],"next_cursor":null}