CLEAR Adapter Routing Balances LLM Safety and Utility
UIUC-CS · hf · 2026-08-24
CLEAR uses a hidden-state gate to continuously modulate a safety low-rank adapter. This approach improves LLM safety while preserving utility on benign inputs, addressing the performance degradation often caused by safety alignment.
More from Research
- CWoMP accepted to EMNLP 2026: Interpretable retrieval-based glossing for endangered languages — fredahshi · 2026-08-24
- SemiAnalysis Open Sources $3M AgentX Benchmark for Agentic Coding Workloads — AccBalanced · 2026-08-24
- Vinci2 Agent Outperforms GPT-5-mini in Proactive Assistance Benchmark — jiqizhixin · 2026-08-24
- OpenAI hiring for Economics of Transformative AI, MATS fellowship applications open — Astral Codex Ten · 2026-08-24
- New "Discovery Episode" Framework Measures AI Scientists by Real Research Cycles — 量子位 · 2026-08-24
- AI Claims Breakthrough on Erdős Problem Transcendence — inductionheads · 2026-08-24