AINeutralarXiv – CS AI · 10h ago6/10
🧠
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
Researchers introduce TF-RefusalBench, a multilingual benchmark measuring over-alignment in large language models used for criminal law tasks in Swiss courts. The study demonstrates that safety guardrails designed to prevent harmful outputs inadvertently compromise legitimate legal work by refusing to process content describing violent crimes, and proposes abliteration as an effective mitigation technique.