{"total":19,"rows":[{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2410.17194","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2412.06370","title":"Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2506.04410","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2408.10608","title":"BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2607.27539","title":"Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2601.23157","title":"No More, No Less: Least-Privilege Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2505.05064","title":"WaterDrum: Watermarking for Data-centric Unlearning Metric","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.10777","title":"Locking Pretrained Weights via Deep Low-Rank Residual Distillation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.06872","title":"Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2610.08778","title":"Sherpa: Teaching LLMs to Teach Adaptively","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}