trends.barnas.net

phenomenon · first seen 19 Oct 2026

harmful fine-tuning

Also: reinforcement learning fine-tuning safety attack

Degradation of safety alignment in language models when they are fine-tuned on downstream data.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

safety alignmentreward function probing