{"total":23,"rows":[{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85,"area":null},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2405.05990","title":"Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models","created":"2024-05-09","cited_by_count":17,"area":null},{"id":"2510.22503","title":"LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery","created":"2025-10-26","cited_by_count":13,"area":null},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2606.25039","title":"LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search","created":"2026-06-23","cited_by_count":7,"area":null},{"id":"2404.17401","title":"Evaluation of Geographical Distortions in Language Models","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2510.00496","title":"Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2505.02172","title":"Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2506.18998","title":"Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2405.05049","title":"Seeds of Stereotypes: A Large-Scale Textual Analysis of Race and Gender Associations with Diseases in Online Sources","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2410.06235","title":"Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2411.13459","title":"SoK: A Systems Perspective on Compound AI Threats and Countermeasures","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2510.01687","title":"Improving AGI Evaluation: A Data Science Perspective","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2606.18767","title":"Output Vector Editing for Memorization Mitigation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.00345","title":"Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.12085","title":"Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}