{"total":24,"rows":[{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"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":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2603.01562","title":"RubricBench: Aligning Model-Generated Rubrics with Human Standards","created":"2026-03-02","cited_by_count":28,"area":"alignment"},{"id":"2504.14716","title":"Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation","created":"2025-04-20","cited_by_count":24,"area":"alignment"},{"id":"2505.11080","title":"BLEUBERI: BLEU is a surprisingly effective reward for instruction following","created":"2025-05-16","cited_by_count":17,"area":"alignment"},{"id":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","cited_by_count":16,"area":"alignment"},{"id":"2505.07271","title":"On the Robustness of Reward Models for Language Model Alignment","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"area":"alignment"},{"id":"2411.00722","title":"Token-level Proximal Policy Optimization for Query Generation","created":"2024-11-01","cited_by_count":7,"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":"2508.08236","title":"Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge","created":"2025-08-11","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":"2507.18802","title":"DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition","created":"2025-07-24","cited_by_count":3,"area":"alignment"},{"id":"2510.20449","title":"LM-mixup: Text Data Augmentation via Language Model based Mixup","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2602.07799","title":"Fairness Aware Reward Optimization","created":"2026-02-08","cited_by_count":1,"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":"2608.21376","title":"On the Role of Citations in Preference Data","created":"2026-07-06","cited_by_count":0,"area":"alignment"},{"id":"2609.31215","title":"DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration","created":"2026-09-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}