LessWrong7 min read
Homeopathic Learning: Diluting Poisoned Fine-Tuning Data Can Strengthen Its Effect
Authors: Matt Clarke*, Jan Dubiński*, James Chua, Simon Schrodi, Owain Evans, Alex Cloud (*- Core contribution)tl;dr. We find that poisoned training data with little effect on its own can create a hidden backdoor once clean, contrasting data is added.
By mclarkeLessWrong

Read the full story
Originally published by LessWrong on Nov 14, 2026.
Comments
Sign in to join the discussion.