{"total":57,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323,"area":"alignment"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2406.07115","title":"Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees","created":"2024-06-11","cited_by_count":38,"area":"lr"},{"id":"2402.00856","title":"Towards Efficient Exact Optimization of Language Model Alignment","created":"2024-02-01","cited_by_count":37,"area":"alignment"},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35,"area":"lr"},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"area":"alignment"},{"id":"2401.12873","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","created":"2024-01-23","cited_by_count":33,"area":"alignment"},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32,"area":"alignment"},{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2301.10684","title":"Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement","created":"2023-01-25","cited_by_count":23,"area":null},{"id":"2212.09710","title":"Continual Learning for Instruction Following from Realtime Feedback","created":"2022-12-19","cited_by_count":22,"area":null},{"id":"2311.02775","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","created":"2023-11-05","cited_by_count":22,"area":"alignment"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"area":"alignment"},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","cited_by_count":19,"area":null},{"id":"2311.09132","title":"Aligning Neural Machine Translation Models: Human Feedback in Training and Inference","created":"2023-11-15","cited_by_count":19,"area":"alignment"},{"id":"2406.18365","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","created":"2024-06-26","cited_by_count":19,"area":null},{"id":"2410.18141","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","created":"2024-10-22","cited_by_count":19,"area":"rag"},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"area":"alignment"},{"id":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2310.10706","title":"Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2011.02511","title":"Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks","created":"2020-11-04","cited_by_count":12,"area":"alignment"},{"id":"2305.12473","title":"Continually Improving Extractive QA via Human Feedback","created":"2023-05-21","cited_by_count":11,"area":null},{"id":"2411.05986","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","created":"2024-11-08","cited_by_count":11,"area":"alignment"},{"id":"2307.08074","title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","created":"2023-07-16","cited_by_count":10,"area":null},{"id":"2307.16246","title":"DRL4Route: A Deep Reinforcement Learning Framework for Pick-up and Delivery Route Prediction","created":"2023-07-30","cited_by_count":10,"area":null},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","cited_by_count":9,"area":"alignment"},{"id":"2601.02036","title":"GDRO: Group-level Reward Post-training Suitable for Diffusion Models","created":"2026-01-05","cited_by_count":8,"area":"diffusion"},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2505.10250","title":"ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2505.24203","title":"Aligning Protein Conformation Ensemble Generation with Physical Feedback","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2312.16430","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling","created":"2023-12-27","cited_by_count":4,"area":"alignment"},{"id":"2408.07294","title":"SumRecom: A Personalized Summarization Approach by Learning from Users' Feedback","created":"2024-08-02","cited_by_count":4,"area":null},{"id":"2311.03056","title":"LitSumm: Large language models for literature summarisation of non-coding RNAs","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2410.02320","title":"Post-edits Are Preferences Too","created":"2024-10-03","cited_by_count":3,"area":"alignment"},{"id":"2504.04740","title":"SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2102.11403","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2503.18347","title":"Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners","created":"2025-03-24","cited_by_count":1,"area":"alignment"},{"id":"2511.22130","title":"Benchmarking In-context Experiential Learning Through Repeated Product Recommendations","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2211.07596","title":"Towards Abstractive Timeline Summarisation using Preference-based Reinforcement Learning","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2501.03008","title":"Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2505.11893","title":"RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving","created":"2025-05-17","cited_by_count":0,"area":"lr"},{"id":"2603.20100","title":"An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models","created":"2026-03-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}