{"total":21,"rows":[{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2404.12272","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","created":"2024-04-18","cited_by_count":144,"area":"alignment"},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"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":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"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":"2406.10288","title":"Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models","created":"2024-06-12","cited_by_count":17,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2603.19311","title":"PrefPO: Pairwise Preference Prompt Optimization","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2604.02174","title":"Quantifying Self-Preservation Bias in Large Language Models","created":"2026-04-02","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":"2510.06391","title":"Reward Model Perspectives: Whose Opinions Do Reward Models Reward?","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2607.07918","title":"Efficient Safety Alignment of Language Models via Latent Personality Traits","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2510.25884","title":"Approximating Human Preferences Using a Multi-Judge Learned System","created":"2025-10-29","cited_by_count":0,"area":"alignment"},{"id":"2511.17256","title":"Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis","created":"2025-11-21","cited_by_count":0,"area":"alignment"},{"id":"2601.17096","title":"Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2609.22170","title":"Multiple latent orderings better predict language model preferences","created":"2026-08-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}