{"total":21,"rows":[{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31,"area":"alignment"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2502.13946","title":"Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region","created":"2025-02-19","cited_by_count":6,"area":"alignment"},{"id":"2508.19697","title":"Safety Alignment Should Be Made More Than Just A Few Attention Heads","created":"2025-08-27","cited_by_count":5,"area":"alignment"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2603.05773","title":"Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models","created":"2026-03-06","cited_by_count":2,"area":"alignment"},{"id":"2509.03985","title":"NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models","created":"2025-09-04","cited_by_count":1,"area":"alignment"},{"id":"2606.28153","title":"Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2509.24713","title":"Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2605.08878","title":"Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2608.01414","title":"No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.27504","title":"Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2610.09600","title":"SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models","created":"2026-10-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}