{"total":15,"rows":[{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"area":"safety"},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76,"area":"safety"},{"id":"2304.10619","title":"\"HOT\" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media","created":"2023-04-20","cited_by_count":45,"area":"safety"},{"id":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"area":"safety"},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2410.13808","title":"De-mark: Watermark Removal in Large Language Models","created":"2024-10-17","cited_by_count":14,"area":"safety"},{"id":"2403.14339","title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning","created":"2024-03-21","cited_by_count":11,"area":"safety"},{"id":"2411.05854","title":"Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators","created":"2024-11-06","cited_by_count":8,"area":"safety"},{"id":"2508.20890","title":"PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance","created":"2025-08-28","cited_by_count":8,"area":"safety"},{"id":"2506.16575","title":"Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System","created":"2025-06-19","cited_by_count":1,"area":"safety"},{"id":"2502.05291","title":"Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet","created":"2025-02-07","cited_by_count":0,"area":"safety"},{"id":"2509.05230","title":"CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models","created":"2025-09-05","cited_by_count":0,"area":"safety"},{"id":"2602.11962","title":"Wisdom of the LLM Crowd: A Large Scale Benchmark of Multi-Label U.S. Election-Related Harmful Social Media Content","created":"2026-02-12","cited_by_count":0,"area":"safety"},{"id":"2605.29667","title":"Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2608.12623","title":"When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers","created":"2026-08-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}