{"total":16,"rows":[{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"area":"alignment"},{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2406.19071","title":"EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization","created":"2024-06-27","cited_by_count":4,"area":"alignment"},{"id":"2505.15795","title":"Reverse Engineering Human Preferences with Reinforcement Learning","created":"2025-05-21","cited_by_count":3,"area":"alignment"},{"id":"2505.19176","title":"Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge","created":"2025-05-25","cited_by_count":3,"area":"alignment"},{"id":"2604.13717","title":"On Cost-Effective LLM-as-a-Judge Improvement Techniques","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2503.22115","title":"Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories","created":"2025-03-28","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":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2601.11344","title":"How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting","created":"2026-01-16","cited_by_count":0,"area":"alignment"},{"id":"2605.26293","title":"CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations","created":"2026-05-25","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":"2607.21632","title":"A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models","created":"2026-07-19","cited_by_count":0,"area":"alignment"},{"id":"2608.29326","title":"StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue","created":"2026-08-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}