{"total":14,"rows":[{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2505.23556","title":"Understanding Refusal in Language Models with Sparse Autoencoders","created":"2025-05-29","cited_by_count":29,"area":"alignment"},{"id":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2510.12355","title":"Fine-grained Analysis of Brain-LLM Alignment through Input Attribution","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","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":"2602.02304","title":"Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.27971","title":"Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2604.27495","title":"Debiasing Reward Models via Causally Motivated Inference-Time Intervention","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2606.08940","title":"Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2606.24622","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2608.15530","title":"Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback","created":"2026-08-16","cited_by_count":0,"area":"alignment"},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"}],"next_cursor":null}