{"total":16,"rows":[{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2402.11746","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","created":"2024-02-19","cited_by_count":112,"area":"alignment"},{"id":"2310.04799","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","created":"2023-10-07","cited_by_count":54,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2505.18126","title":"Reward Model Overoptimisation in Iterated RLHF","created":"2025-05-23","cited_by_count":12,"area":"alignment"},{"id":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2506.16078","title":"Probing the Robustness of Large Language Models Safety to Latent Perturbations","created":"2025-06-19","cited_by_count":4,"area":"alignment"},{"id":"2404.10306","title":"Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models","created":"2024-04-16","cited_by_count":3,"area":"alignment"},{"id":"2502.16433","title":"Sequence-level Large Language Model Training with Contrastive Preference Optimization","created":"2025-02-23","cited_by_count":3,"area":"alignment"},{"id":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2505.05736","title":"Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications","created":"2025-05-09","cited_by_count":0,"area":"alignment"},{"id":"2506.18331","title":"End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards","created":"2025-06-23","cited_by_count":0,"area":"alignment"}],"next_cursor":null}