Causal evidence that language models use confidence to drive behaviour
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
Nature Machine Intelligence, Published online: 07 September 2026; doi:10.1038/s42256-026-01293-x Kumaran et al. show that large language models making decisions on when to answer a question or abstain from answering can be influenced by boosting or suppressing confidence signals in the model.
Read the full story at Nature Machine Intelligence ↗
Timeline · 1 report
- 2026-09-07 00:00 · Nature Machine Intelligence
Causal evidence that language models use confidence to drive behaviour