{"total":73,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"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":"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":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119,"area":"alignment"},{"id":"2308.01320","title":"DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales","created":"2023-08-02","cited_by_count":108,"area":"alignment"},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38,"area":"alignment"},{"id":"2406.14088","title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation","created":"2024-06-20","cited_by_count":37,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28,"area":"alignment"},{"id":"2310.01581","title":"On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?","created":"2023-10-02","cited_by_count":26,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25,"area":"alignment"},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23,"area":"alignment"},{"id":"2310.02456","title":"Learning Optimal Advantage from Preferences and Mistaking it for Reward","created":"2023-10-03","cited_by_count":19,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"area":"alignment"},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17,"area":"alignment"},{"id":"2507.11316","title":"Internal Value Alignment in Large Language Models through Controlled Value Vector Activation","created":"2025-07-15","cited_by_count":16,"area":"alignment"},{"id":"2403.08309","title":"HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback","created":"2024-03-13","cited_by_count":15,"area":"alignment"},{"id":"2509.07150","title":"PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design","created":"2025-09-08","cited_by_count":14,"area":"alignment"},{"id":"2312.11819","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","created":"2023-12-19","cited_by_count":13,"area":"alignment"},{"id":"2402.16030","title":"Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration","created":"2024-02-25","cited_by_count":13,"area":"alignment"},{"id":"2504.07091","title":"AssistanceZero: Scalably Solving Assistance Games","created":"2025-04-09","cited_by_count":10,"area":"alignment"},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2505.12225","title":"Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling","created":"2025-05-18","cited_by_count":9,"area":"alignment"},{"id":"2506.04463","title":"Aligning Large Language Models with Implicit Preferences from User-Generated Content","created":"2025-06-04","cited_by_count":9,"area":"alignment"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2310.15758","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","created":"2023-10-24","cited_by_count":7,"area":"alignment"},{"id":"2407.15229","title":"A Practical Analysis of Human Alignment with *PO","created":"2024-07-21","cited_by_count":7,"area":"alignment"},{"id":"2408.03618","title":"A Logical Fallacy-Informed Framework for Argument Generation","created":"2024-08-07","cited_by_count":7,"area":"alignment"},{"id":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2503.14329","title":"EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment","created":"2025-03-18","cited_by_count":6,"area":"alignment"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","cited_by_count":6,"area":"alignment"},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2404.16020","title":"Investigating Adversarial Trigger Transfer in Large Language Models","created":"2024-04-24","cited_by_count":5,"area":"alignment"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2501.06164","title":"Model Alignment Search","created":"2025-01-10","cited_by_count":3,"area":"alignment"},{"id":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3,"area":"alignment"},{"id":"2601.12535","title":"Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning","created":"2026-01-18","cited_by_count":3,"area":"alignment"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2603.10938","title":"Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control","created":"2026-03-11","cited_by_count":2,"area":"alignment"},{"id":"2604.08326","title":"ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection","created":"2026-04-09","cited_by_count":2,"area":"alignment"},{"id":"2604.12086","title":"Robust Optimization for Mitigating Reward Hacking with Correlated Proxies","created":"2026-04-13","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2505.12322","title":"Model alignment using inter-modal bridges","created":"2025-05-18","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","created":"2025-08-21","cited_by_count":1,"area":"alignment"},{"id":"2509.23667","title":"Why Alignment Must Precede Distillation: A Minimal Working Explanation","created":"2025-09-28","cited_by_count":1,"area":"alignment"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2410.01858","title":"Long-range gene expression prediction with token alignment of large language model","created":"2024-10-02","cited_by_count":0,"area":"alignment"},{"id":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","cited_by_count":0,"area":"alignment"},{"id":"2506.18331","title":"End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards","created":"2025-06-23","cited_by_count":0,"area":"alignment"},{"id":"2507.20566","title":"Unlearning of Knowledge Graph Embedding via Preference Optimization","created":"2025-07-28","cited_by_count":0,"area":"alignment"},{"id":"2508.09937","title":"A Comprehensive Evaluation framework of Alignment Techniques for LLMs","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2602.03171","title":"StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret Modeling","created":"2026-02-03","cited_by_count":0,"area":"alignment"},{"id":"2605.17342","title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment","created":"2026-05-17","cited_by_count":0,"area":"alignment"},{"id":"2605.21558","title":"From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.03248","title":"Unbiased Alignment for Large Language Models with Noisy Preferences","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.14147","title":"Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak","created":"2026-07-14","cited_by_count":0,"area":"alignment"},{"id":"2607.16242","title":"TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment","created":"2026-06-26","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":"2608.30597","title":"PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.29421","title":"Rufus-Air: An Open LLM Post-Training Recipe","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2610.17827","title":"Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents","created":"2026-10-13","cited_by_count":0,"area":"alignment"},{"id":"2610.19365","title":"DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}