{"total":21,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"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":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2410.21545","title":"CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling","created":"2024-10-28","cited_by_count":22,"area":"alignment"},{"id":"2412.05469","title":"Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization","created":"2024-12-06","cited_by_count":20,"area":"alignment"},{"id":"2307.01139","title":"SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions","created":"2023-07-03","cited_by_count":19,"area":"alignment"},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2512.11838","title":"D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space","created":"2025-12-03","cited_by_count":2,"area":"alignment"},{"id":"2312.05503","title":"Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models","created":"2023-12-09","cited_by_count":1,"area":"alignment"},{"id":"2308.05585","title":"Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer Length","created":"2023-08-10","cited_by_count":0,"area":"alignment"},{"id":"2510.02561","title":"Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback","created":"2025-10-02","cited_by_count":0,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2607.28669","title":"LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment","created":"2026-07-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}