2 papers
cs.LG2026
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
cs.HC2026
PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
Qiyu Li, Yuen Sum Wong, Yuen Kei Wong +2
NIST's Privacy Risk Assessment Methodology (PRAM) provides a structured framework for privacy experts to assess privacy risks. However, its complexity and reliance on expert knowle…