{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"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":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"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":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"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":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"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":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406},{"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":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"1808.08949","title":"Dissecting Contextual Word Embeddings: Architecture and Representation","created":"2018-08-27","cited_by_count":146},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143},{"id":"1909.10773","title":"Sign-OPT: A Query-Efficient Hard-label Adversarial Attack","created":"2019-09-24","cited_by_count":120},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114},{"id":"1507.08752","title":"An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback","created":"2015-07-31","cited_by_count":111},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"1910.12166","title":"Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization","created":"2019-10-27","cited_by_count":47},{"id":"2003.13001","title":"Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling","created":"2020-03-29","cited_by_count":46},{"id":"1606.00498","title":"A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order","created":"2016-06-01","cited_by_count":44},{"id":"1911.06317","title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","created":"2019-11-14","cited_by_count":43},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43},{"id":"2203.11382","title":"Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes","created":"2022-03-21","cited_by_count":42},{"id":"2308.02312","title":"Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions","created":"2023-08-04","cited_by_count":42},{"id":"2008.08170","title":"Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization","created":"2020-08-18","cited_by_count":40},{"id":"2303.03751","title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles","created":"2023-03-07","cited_by_count":35},{"id":"2307.04504","title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","created":"2023-07-10","cited_by_count":23},{"id":"1711.07693","title":"Regret Analysis for Continuous Dueling Bandit","created":"2017-11-21","cited_by_count":22},{"id":"1911.05934","title":"Multi-Attribute Bayesian Optimization With Interactive Preference Learning","created":"2019-11-14","cited_by_count":21},{"id":"2010.02479","title":"A One-bit, Comparison-Based Gradient Estimator","created":"2020-10-06","cited_by_count":16},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12},{"id":"1409.3912","title":"Parallel Distributed Block Coordinate Descent Methods based on Pairwise Comparison Oracle","created":"2014-09-13","cited_by_count":2}],"next_cursor":null}