{"total":19,"rows":[{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2512.12775","title":"Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions","created":"2025-12-14","cited_by_count":12,"area":null},{"id":"2512.24848","title":"PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI","created":"2025-12-31","cited_by_count":12,"area":null},{"id":"2501.07849","title":"The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation","created":"2025-01-14","cited_by_count":10,"area":null},{"id":"2601.18572","title":"One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization","created":"2026-01-26","cited_by_count":9,"area":null},{"id":"2509.19364","title":"The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior","created":"2025-09-18","cited_by_count":8,"area":null},{"id":"2505.15805","title":"Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2509.18293","title":"Evaluating Large Language Models for Detecting Antisemitism","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2601.11000","title":"When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2506.02431","title":"From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2512.10058","title":"Mind the Gap! Pathways Towards Unifying AI Safety and Ethics Research","created":"2025-12-10","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2607.02047","title":"OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2601.09141","title":"Identity-Robust Language Model Generation via Content Integrity Preservation","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2510.10142","title":"Debiasing LLMs by Masking Unfairness-Driving Attention Heads","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.14506","title":"Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.08187","title":"Large Language Models in Peer-Run Community Behavioral Health Services: Understanding Peer Specialists and Service Users' Perspectives on Opportunities, Risks, and Mitigation Strategies","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.19144","title":"UGID: Unified Graph Isomorphism for Debiasing Large Language Models","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}