{"total":49,"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724,"area":"alignment"},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32,"area":"alignment"},{"id":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2404.19409","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","created":"2024-04-30","cited_by_count":20,"area":"alignment"},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","cited_by_count":19,"area":"alignment"},{"id":"2406.16897","title":"InstructPatentGPT: Training patent language models to follow instructions with human feedback","created":"2024-05-25","cited_by_count":19,"area":"alignment"},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14,"area":"alignment"},{"id":"2410.07304","title":"The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making","created":"2024-10-09","cited_by_count":12,"area":"alignment"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2402.14228","title":"COPR: Continual Human Preference Learning via Optimal Policy Regularization","created":"2024-02-22","cited_by_count":9,"area":"alignment"},{"id":"2410.11348","title":"RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals","created":"2024-10-15","cited_by_count":8,"area":"alignment"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2310.16681","title":"BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?","created":"2023-10-25","cited_by_count":7,"area":"alignment"},{"id":"2309.08583","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","created":"2023-09-15","cited_by_count":5,"area":"alignment"},{"id":"2312.01957","title":"Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective","created":"2023-12-04","cited_by_count":5,"area":"alignment"},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2501.17112","title":"Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI","created":"2025-01-28","cited_by_count":4,"area":"alignment"},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2506.15717","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2605.01205","title":"SRA: Span Representation Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":3,"area":"alignment"},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2405.17618","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","created":"2024-05-27","cited_by_count":2,"area":"alignment"},{"id":"2502.11853","title":"StructTransform: A Scalable Attack Surface for Safety-Aligned Large Language Models","created":"2025-02-17","cited_by_count":2,"area":"alignment"},{"id":"2506.02479","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2603.19741","title":"FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment","created":"2026-03-20","cited_by_count":2,"area":"alignment"},{"id":"2408.02651","title":"Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?","created":"2024-08-05","cited_by_count":1,"area":"alignment"},{"id":"2409.07335","title":"Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model Generalization","created":"2024-09-11","cited_by_count":1,"area":"alignment"},{"id":"2410.17126","title":"Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards","created":"2024-10-22","cited_by_count":1,"area":"alignment"},{"id":"2509.21351","title":"Random Direct Preference Optimization for Radiography Report Generation","created":"2025-09-19","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":"2604.11121","title":"BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection","created":"2026-04-13","cited_by_count":1,"area":"alignment"},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2602.05056","title":"Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2604.00773","title":"From Baselines to Preferences: A Comparative Study of LoRA/QLoRA and Preference Optimization for Mental Health Text Classification","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"id":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","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":"2610.09209","title":"Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation","created":"2026-10-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}