{"total":79,"rows":[{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394,"area":"alignment"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2406.14868","title":"Direct Multi-Turn Preference Optimization for Language Agents","created":"2024-06-21","cited_by_count":64,"area":"agents"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2402.04210","title":"Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors","created":"2024-02-06","cited_by_count":25,"area":"agents"},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2405.19806","title":"Preference Alignment with Flow Matching","created":"2024-05-30","cited_by_count":11,"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":"2409.05622","title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies","created":"2024-09-09","cited_by_count":10,"area":"diffusion"},{"id":"2404.04920","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment","created":"2024-04-07","cited_by_count":9,"area":"diffusion"},{"id":"2404.11288","title":"A Preference-driven Paradigm for Enhanced Translation with Large Language Models","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2506.09176","title":"Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2402.15757","title":"Batch Active Learning of Reward Functions from Human Preferences","created":"2024-02-24","cited_by_count":8,"area":null},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2410.11584","title":"DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2509.05882","title":"Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes","created":"2025-09-07","cited_by_count":7,"area":"agents"},{"id":"2312.01057","title":"RLHF and IIA: Perverse Incentives","created":"2023-12-02","cited_by_count":6,"area":null},{"id":"2405.16681","title":"Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization","created":"2024-05-26","cited_by_count":6,"area":"alignment"},{"id":"2503.20105","title":"Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations","created":"2025-03-25","cited_by_count":6,"area":"agents"},{"id":"2511.12573","title":"Mitigating Length Bias in RLHF through a Causal Lens","created":"2025-11-16","cited_by_count":6,"area":"alignment"},{"id":"2606.12372","title":"UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning","created":"2026-06-10","cited_by_count":6,"area":"agents"},{"id":"2405.03113","title":"Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning","created":"2024-05-06","cited_by_count":5,"area":"deeprl"},{"id":"2311.09136","title":"Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2406.08842","title":"ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions","created":"2024-06-13","cited_by_count":4,"area":"alignment"},{"id":"2501.06416","title":"Influencing Humans to Conform to Preference Models for RLHF","created":"2025-01-11","cited_by_count":4,"area":"alignment"},{"id":"2507.23391","title":"Policy Learning from Large Vision-Language Model Feedback without Reward Modeling","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2501.09444","title":"Solving the Unsolvable: Translating Case Law in Hong Kong","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2505.18595","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","created":"2025-05-24","cited_by_count":3,"area":"agents"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2510.01545","title":"Predictive Preference Learning from Human Interventions","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2502.02628","title":"e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration","created":"2025-02-04","cited_by_count":2,"area":"alignment"},{"id":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2503.10228","title":"Policy Teaching via Data Poisoning in Learning from Human Preferences","created":"2025-03-13","cited_by_count":2,"area":"alignment"},{"id":"2503.15801","title":"Disentangling Uncertainties by Learning Compressed Data Representation","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2503.19523","title":"One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF","created":"2025-03-25","cited_by_count":2,"area":"lr"},{"id":"2505.00490","title":"Optimal Interactive Learning on the Job via Facility Location Planning","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","cited_by_count":2,"area":"alignment"},{"id":"2509.21828","title":"Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2602.00886","title":"RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback","created":"2026-01-31","cited_by_count":2,"area":"diffusion"},{"id":"2411.00361","title":"Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach","created":"2024-11-01","cited_by_count":1,"area":"alignment"},{"id":"2602.01357","title":"Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning","created":"2026-02-01","cited_by_count":1,"area":"synth"},{"id":"2603.03280","title":"How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference","created":"2026-03-03","cited_by_count":1,"area":"alignment"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2506.08998","title":"On Monotonicity in AI Alignment","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2511.09537","title":"NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2606.05382","title":"Synthetic Contrastive Reasoning for Multi-Table Q&A","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2606.18703","title":"Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.20272","title":"Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.18258","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"},{"id":"2610.00715","title":"Robust Nash Alignment under Preference Uncertainty","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.13755","title":"Matched-Context Group Policy Optimization for LLM Agent Training","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}