{"list":"other","total":52,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"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":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","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":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"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":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","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":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81},{"id":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54},{"id":"2312.02179","title":"Training Chain-of-Thought via Latent-Variable Inference","created":"2023-11-28","cited_by_count":47},{"id":"2410.10630","title":"Thinking LLMs: General Instruction Following with Thought Generation","created":"2024-10-14","cited_by_count":45},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29},{"id":"2410.09302","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","created":"2024-10-11","cited_by_count":22}],"next_cursor":null}