{"total":21,"rows":[{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"area":"safety"},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","cited_by_count":17,"area":"safety"},{"id":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2508.09603","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","created":"2025-08-13","cited_by_count":7,"area":"safety"},{"id":"2510.02962","title":"Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking","created":"2025-10-03","cited_by_count":5,"area":"safety"},{"id":"2411.12600","title":"Provable unlearning in topic modeling and downstream tasks","created":"2024-11-19","cited_by_count":4,"area":"safety"},{"id":"2403.15740","title":"Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training","created":"2024-03-23","cited_by_count":3,"area":"safety"},{"id":"2412.21123","title":"ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation","created":"2024-12-30","cited_by_count":3,"area":"safety"},{"id":"2501.17501","title":"How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning","created":"2025-01-29","cited_by_count":3,"area":"safety"},{"id":"2510.17620","title":"Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2507.07754","title":"One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting","created":"2025-07-10","cited_by_count":2,"area":"safety"},{"id":"2508.01324","title":"Towards Evaluation for Real-World LLM Unlearning","created":"2025-08-02","cited_by_count":2,"area":"safety"},{"id":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2512.00837","title":"WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking","created":"2025-11-30","cited_by_count":0,"area":"safety"},{"id":"2601.12937","title":"On the Evidentiary Limits of Membership Inference for Copyright Auditing","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.00577","title":"SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution","created":"2026-01-31","cited_by_count":0,"area":"safety"}],"next_cursor":null}