{"total":82,"rows":[{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"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,"area":"alignment"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"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":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"area":"mllm"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55,"area":null},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2504.10160","title":"MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning","created":"2025-04-14","cited_by_count":48,"area":"lr"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2302.13344","title":"Tailoring Language Generation Models under Total Variation Distance","created":"2023-02-26","cited_by_count":27,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24,"area":"alignment"},{"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,"area":"lr"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2109.00527","title":"Boosting Search Engines with Interactive Agents","created":"2021-09-01","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":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","created":"2023-08-04","cited_by_count":15,"area":null},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"area":"alignment"},{"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":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2310.16763","title":"SuperHF: Supervised Iterative Learning from Human Feedback","created":"2023-10-25","cited_by_count":10,"area":"alignment"},{"id":"2401.15670","title":"YODA: Teacher-Student Progressive Learning for Language Models","created":"2024-01-28","cited_by_count":10,"area":"distill"},{"id":"2406.12168","title":"BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment","created":"2024-06-18","cited_by_count":9,"area":"alignment"},{"id":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"area":null},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2207.08583","title":"MAD for Robust Reinforcement Learning in Machine Translation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2506.14574","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization","created":"2025-06-17","cited_by_count":5,"area":"alignment"},{"id":"2112.08670","title":"Amortized Noisy Channel Neural Machine Translation","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2206.13974","title":"Joint Generator-Ranker Learning for Natural Language Generation","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2406.11581","title":"Style Transfer with Multi-iteration Preference Optimization","created":"2024-06-17","cited_by_count":4,"area":"alignment"},{"id":"2509.16990","title":"Advancing Speech Understanding in Speech-Aware Language Models with GRPO","created":"2025-09-21","cited_by_count":4,"area":"lr"},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2201.08810","title":"GAP-Gen: Guided Automatic Python Code Generation","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2206.01011","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2210.03053","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2402.13936","title":"Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2503.10669","title":"UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality","created":"2025-03-10","cited_by_count":2,"area":"alignment"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2101.12640","title":"Enhancing the Transformer Decoder with Transition-based Syntax","created":"2021-01-29","cited_by_count":1,"area":null},{"id":"2102.11403","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.14694","title":"GROOT: Corrective Reward Optimization for Generative Sequential Labeling","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2305.13667","title":"Optimizing Non-Autoregressive Transformers with Contrastive Learning","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2405.01280","title":"Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation","created":"2024-05-02","cited_by_count":1,"area":"alignment"},{"id":"2603.17952","title":"Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2109.13097","title":"Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2211.16550","title":"Soft Alignment Objectives for Robust Adaptation of Language Generation","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2407.06990","title":"Segment-Based Interactive Machine Translation for Pre-trained Models","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.19152","title":"VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}