{"total":13,"rows":[{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"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":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2506.11673","title":"Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2403.16584","title":"Can Large Language Models (or Humans) Disentangle Text?","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2505.03997","title":"Quiet Feature Learning in Algorithmic Tasks","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2608.06891","title":"SkillEval: Decomposing Agent Skill Quality into Interpretable Signals","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.10566","title":"Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2403.16142","title":"What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2608.10462","title":"Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}