{"total":32,"rows":[{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19,"area":"safety"},{"id":"2503.00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","created":"2025-03-01","cited_by_count":18,"area":"safety"},{"id":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"area":"safety"},{"id":"2410.05583","title":"NegMerge: Sign-Consensual Weight Merging for Machine Unlearning","created":"2024-10-08","cited_by_count":9,"area":"safety"},{"id":"2406.07188","title":"Merging Improves Self-Critique Against Jailbreak Attacks","created":"2024-06-11","cited_by_count":8,"area":"safety"},{"id":"2506.03117","title":"Targeted Forgetting of Image Subgroups in CLIP Models","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2409.19173","title":"HM3: Heterogeneous Multi-Class Model Merging","created":"2024-09-27","cited_by_count":3,"area":"safety"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","cited_by_count":3,"area":"safety"},{"id":"2504.19333","title":"Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing","created":"2025-04-27","cited_by_count":3,"area":"safety"},{"id":"2508.12622","title":"Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes","created":"2025-08-18","cited_by_count":2,"area":"safety"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2607.01686","title":"WARP: Weight-Space Analysis for Recovering Training Data Portfolios","created":"2026-07-02","cited_by_count":1,"area":"safety"},{"id":"2607.19442","title":"Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification","created":"2026-07-21","cited_by_count":1,"area":"safety"},{"id":"2511.18660","title":"Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2602.06887","title":"Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2602.23798","title":"MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"safety"},{"id":"2604.17384","title":"Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion","created":"2026-04-19","cited_by_count":0,"area":"safety"},{"id":"2606.31748","title":"Addressing Over-Refusal in LLMs with Competing Rewards","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2607.20435","title":"Making Open-Source Text LLM Watermarks Durable Against Merging","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2607.27240","title":"Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition","created":"2026-07-26","cited_by_count":0,"area":"safety"},{"id":"2608.26506","title":"A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.37076","title":"UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.38895","title":"Unmerge: Efficient Machine Unlearning via Task Arithmetic","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.14701","title":"Towards Merging-conditional Backdoor Unalignment against Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}