{"total":60,"rows":[{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100,"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":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"area":"alignment"},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2304.11490","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","created":"2023-04-22","cited_by_count":64,"area":"alignment"},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44,"area":"alignment"},{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"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":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2406.17453","title":"Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain","created":"2024-06-25","cited_by_count":21,"area":"alignment"},{"id":"2403.01304","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","created":"2024-03-02","cited_by_count":20,"area":"alignment"},{"id":"2410.04064","title":"Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback","created":"2024-10-05","cited_by_count":17,"area":"alignment"},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2410.03145","title":"Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback","created":"2024-10-04","cited_by_count":15,"area":"alignment"},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2402.16567","title":"Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL","created":"2024-02-26","cited_by_count":14,"area":"alignment"},{"id":"2405.09223","title":"Word Alignment as Preference for Machine Translation","created":"2024-05-15","cited_by_count":14,"area":"alignment"},{"id":"2411.08302","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","created":"2024-11-13","cited_by_count":10,"area":"alignment"},{"id":"2501.18457","title":"CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering","created":"2025-01-30","cited_by_count":10,"area":"alignment"},{"id":"2402.10184","title":"Reward Generalization in RLHF: A Topological Perspective","created":"2024-02-15","cited_by_count":9,"area":"alignment"},{"id":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2410.03818","title":"Large Language Models can be Strong Self-Detoxifiers","created":"2024-10-04","cited_by_count":7,"area":"alignment"},{"id":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","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":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"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":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5,"area":"alignment"},{"id":"2407.14477","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment","created":"2024-07-19","cited_by_count":5,"area":"alignment"},{"id":"2410.10392","title":"Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search","created":"2024-10-14","cited_by_count":5,"area":"alignment"},{"id":"2405.20215","title":"TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models","created":"2024-05-30","cited_by_count":4,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2509.13244","title":"Evaluating LLM Alignment on Personality Inference from Real-World Interview Data","created":"2025-09-16","cited_by_count":4,"area":"alignment"},{"id":"2412.04305","title":"ALMA: Alignment with Minimal Annotation","created":"2024-12-05","cited_by_count":3,"area":"alignment"},{"id":"2608.06377","title":"Learning When to Trust via Selective Context Preference Optimization","created":"2026-08-06","cited_by_count":3,"area":"alignment"},{"id":"2510.21883","title":"Language Ranker: A Lightweight Ranking framework for LLM Decoding","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2601.07149","title":"Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling","created":"2026-01-12","cited_by_count":2,"area":"alignment"},{"id":"2410.22203","title":"Democratizing Reward Design for Personal and Representative Value-Alignment","created":"2024-10-29","cited_by_count":1,"area":"alignment"},{"id":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2509.22732","title":"Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks","created":"2025-09-25","cited_by_count":1,"area":"alignment"},{"id":"2510.19265","title":"Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2511.23184","title":"Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction","created":"2025-11-28","cited_by_count":1,"area":"alignment"},{"id":"2601.21452","title":"SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2506.08965","title":"GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2506.11098","title":"Debiasing Online Preference Learning via Preference Feature Preservation","created":"2025-06-06","cited_by_count":0,"area":"alignment"},{"id":"2510.25014","title":"Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading","created":"2025-10-28","cited_by_count":0,"area":"alignment"},{"id":"2606.21502","title":"Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation","created":"2026-06-19","cited_by_count":0,"area":"alignment"},{"id":"2608.14629","title":"Inference-Time Mitigation of Adversarial Political Bias in Large Language Models","created":"2026-07-24","cited_by_count":0,"area":"alignment"}],"next_cursor":null}