Nathaniel Daw

Identifiers

• name variant Nathaniel Daw 0.60 · backfill

Papers (2)

1. How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals cs.LG · 2026 · author #5
2. Causal Evidence that Language Models use Confidence to Drive Behavior cs.LG · 2026 · author #2

Mentions

• 2603.22161 #2 · arxiv_oai · confidence 0.70 Nathaniel Daw

Frequent Coauthors

• Dharshan Kumaran 2 shared papers
• Petar Veli\v{c}kovi\'c 2 shared papers
• Simon Osindero 2 shared papers
• Viorica Patraucean 2 shared papers