Our readingWhat is a korrent?
Using supervised fine-tuning to teach a language model new knowledge risks increasing its hallucination rate.
Drawn from what Lilian Weng said
SubjectLLMs
What Lilian Weng actually said
- Lilian Weng Machine-learning researcher
These empirical results from Gekhman et al. (2024) point out the risk of using supervised fine-tuning for updating LLMs' knowledge.
Where this was said
↗Extrinsic Hallucinations in LLMslilianweng.github.io
All 2 korrents from this piecethis one is 2nd
Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooRelated korrents
Shared subject first, then similar wording. They may agree or disagree.