{"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":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2509.08075","title":"No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models","created":"2025-09-09","cited_by_count":9,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2507.11544","title":"The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.19005","title":"Dynamic Evaluation for Oversensitivity in LLMs","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2502.01015","title":"Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2602.04521","title":"$C$-$\\Delta\\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2607.05842","title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2603.13318","title":"Residual Stream Analysis of Overfitting And Structural Disruptions","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.15789","title":"A Systematic Study of Training-Free Methods for Trustworthy Large Language Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2607.04846","title":"Pretraining Curricula Enable Selective Fine-tuning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.18093","title":"Abliteration Mitigation via Refusal Aliases","created":"2026-06-07","cited_by_count":0,"area":null}],"next_cursor":null}