{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"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":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136},{"id":"1805.06087","title":"Learning to Write with Cooperative Discriminators","created":"2018-05-16","cited_by_count":119},{"id":"2402.10963","title":"GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements","created":"2024-02-13","cited_by_count":103},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40}],"next_cursor":null}