Our readingWhat is a korrent?
Chain-of-thought explanations from language models can be biased because training does not explicitly reward faithful reasoning.
Drawn from what Lilian Weng said
SubjectLLMs
Mental modelIncentives
What Lilian Weng actually said
- Lilian Weng Machine-learning researcher
model CoTs could be biased due to lack of explicit training objectives aimed at encouraging faithful reasoning
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.