{"total":13,"rows":[{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2506.00085","title":"COSMIC: Generalized Refusal Direction Identification in LLM Activations","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2603.04045","title":"Inference-Time Toxicity Mitigation in Protein Language Models","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2608.11735","title":"Locating and Controlling Implicit Personalization in Large Language Models","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2601.02906","title":"Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.17836","title":"Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.32530","title":"Activation Flow: Manufacturing Activations for Steering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.01054","title":"Capturing In-Context Learning Dynamics with Task Operators","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}