Legilimens: Practical and Unified Content Moderation forLarge Language Model Services
arxiv.org · 5,975 words · saved by 1 readers
N/A
Legilimens: Practical and Unified Content Moderation for Large Language Model Services Jialin Wu∗ Jiangyi Deng∗ Shengyuan Pang Zhejiang University Zhejiang University Zhejiang University Hangzhou, Zhejiang,…
saved by
related reading
- RigorLLM: Resilient Guardrails for Large Language Models against Undesired Contentarxiv.org
- 2025.naacl-long.441.pdfaclanthology.org
- LLM-Mod: Can Large Language Models Assist Content Moderation?koustuv.com
- 2312.06674arxiv.org
- [2502.05209] Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilitiesarxiv.org
- Large Language Diffusion Modelsarxiv.org
- [2512.11949] Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitorsarxiv.org
- Self-Adapting Language Modelsarxiv.org
- 2408.12798arxiv.org
- Foundational Challenges in Assuring Alignment and Safety of Large Language Modelsarxiv.org
- 2401.02415.pdfarxiv.org
- [2412.00543] Evaluating the Consistency of LLM Evaluatorsarxiv.org