{"list":"other","total":55,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"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":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"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":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"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":"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":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"2406.09279","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","created":"2024-06-13","cited_by_count":107},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93},{"id":"1905.13416","title":"Fine-Grained Spoiler Detection from Large-Scale Review Corpora","created":"2019-05-31","cited_by_count":77},{"id":"2406.11827","title":"WPO: Enhancing RLHF with Weighted Preference Optimization","created":"2024-06-17","cited_by_count":54},{"id":"2403.19270","title":"sDPO: Don't Use Your Data All at Once","created":"2024-03-28","cited_by_count":46},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40},{"id":"2408.04614","title":"Better Alignment with Instruction Back-and-Forth Translation","created":"2024-08-08","cited_by_count":16},{"id":"2407.06542","title":"LIONs: An Empirically Optimized Approach to Align Language Models","created":"2024-07-09","cited_by_count":7}],"next_cursor":null}