{"list":"other","total":52,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"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":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"2308.07921","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","created":"2023-08-15","cited_by_count":166},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93},{"id":"2311.09724","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","created":"2023-11-16","cited_by_count":85},{"id":"2109.03034","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","created":"2021-09-07","cited_by_count":82},{"id":"1812.03381","title":"Learning Montezuma's Revenge from a Single Demonstration","created":"2018-12-08","cited_by_count":80},{"id":"1704.03073","title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","created":"2017-04-10","cited_by_count":63},{"id":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43},{"id":"1607.05077","title":"Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay","created":"2016-07-18","cited_by_count":22},{"id":"2309.11054","title":"Design of Chain-of-Thought in Math Problem Solving","created":"2023-09-20","cited_by_count":12},{"id":"2001.00406","title":"Rethinking Defeasible Reasoning: A Scalable Approach","created":"2020-01-02","cited_by_count":4}],"next_cursor":null}