{"total":22,"rows":[{"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":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30,"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":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2505.02009","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","created":"2025-05-04","cited_by_count":9,"area":"safety"},{"id":"2503.02776","title":"Implicit Bias in LLMs: A Survey","created":"2025-03-04","cited_by_count":8,"area":"safety"},{"id":"2510.23891","title":"PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2510.21946","title":"$\\delta$-STEAL: LLM Stealing Attack with Local Differential Privacy","created":"2025-10-24","cited_by_count":3,"area":"safety"},{"id":"2503.05721","title":"What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets","created":"2025-02-17","cited_by_count":2,"area":"safety"},{"id":"2506.05594","title":"SoK: Are Watermarks in LLMs Ready for Deployment?","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2508.06467","title":"LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2511.08637","title":"How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets","created":"2025-11-10","cited_by_count":2,"area":"safety"},{"id":"2605.23175","title":"Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection","created":"2026-05-22","cited_by_count":1,"area":"safety"},{"id":"2503.15205","title":"A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models","created":"2025-03-19","cited_by_count":0,"area":"safety"},{"id":"2508.02312","title":"Data Security in Large Language Models: Risks, Defense, and Directions","created":"2025-08-04","cited_by_count":0,"area":"safety"},{"id":"2509.12574","title":"Yet Another Watermark for Large Language Models","created":"2025-09-16","cited_by_count":0,"area":"safety"},{"id":"2510.09471","title":"Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World","created":"2025-10-10","cited_by_count":0,"area":"safety"},{"id":"2605.05427","title":"The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models","created":"2026-05-06","cited_by_count":0,"area":"safety"},{"id":"2606.05936","title":"Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2609.12472","title":"TripPattern: A Pattern-based Text Watermarking Method for Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"safety"}],"next_cursor":null}