{"total":34,"rows":[{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724,"area":"alignment"},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"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":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63,"area":"alignment"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"area":"alignment"},{"id":"2503.20491","title":"VPO: Aligning Text-to-Video Generation Models with Prompt Optimization","created":"2025-03-26","cited_by_count":30,"area":"alignment"},{"id":"2311.08685","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","created":"2023-11-15","cited_by_count":27,"area":"alignment"},{"id":"2403.11124","title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment","created":"2024-03-17","cited_by_count":26,"area":"alignment"},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"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":"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":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13,"area":"alignment"},{"id":"2402.13919","title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2024-02-21","cited_by_count":12,"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":"2310.20033","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2023-10-30","cited_by_count":5,"area":"alignment"},{"id":"2407.02302","title":"Towards Human Understanding of Paraphrase Types in Large Language Models","created":"2024-07-02","cited_by_count":2,"area":"alignment"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"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":"2505.07886","title":"PLHF: Prompt Optimization with Few-Shot Human Feedback","created":"2025-05-11","cited_by_count":1,"area":"alignment"},{"id":"2606.00083","title":"From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models","created":"2026-05-22","cited_by_count":1,"area":"alignment"},{"id":"2507.08109","title":"Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing","created":"2025-07-10","cited_by_count":0,"area":"alignment"},{"id":"2606.24004","title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","created":"2026-06-22","cited_by_count":0,"area":"alignment"},{"id":"2607.23153","title":"In-Context Learning as Implicit Policy Gradient","created":"2026-07-25","cited_by_count":0,"area":"alignment"},{"id":"2608.26779","title":"Instruction Quality Matters: Refining Instructions for Effective Preference Learning","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2608.30842","title":"Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment","created":"2026-08-31","cited_by_count":0,"area":"alignment"}],"next_cursor":null}