Training on rationales alone cuts false refusals without hurting safety
POSTECH · hf · 2026-09-08
POSTECH's structural analysis decomposes safety-tuning responses into refusal statements and rationales, showing that training on rationales alone reduces false refusals in LLMs while preserving safety.
More from Research
- Thousands of AI drug discovery firms, only a handful of end-to-end automated labs — robleclerc · 2026-09-08
- Insilico's AI drug Rentosertib shows 3-4 year biological age reversal in 12 weeks — NinaDSchick · 2026-09-08
- Speridlabs releases ENEAS, a text-promptable tracking method claiming gains over SAM3 — joecole · 2026-09-08
- UCL's Large Discovery Models hit SOTA, 2.4x LLM reflection on experiment search — jiqizhixin · 2026-09-08
- First IAB workshop on agent behavior draws 260 submissions, seeks reviewers — mdredze · 2026-09-08
- Dr. Claw: Open-Source AI Scientist Workspace Wrapping Coding Agents for Auditable Research — Dingjie Song · 2026-09-08