Dharshan Kumaran

Identifiers

• name variant Dharshan Kumaran 0.60 · backfill

Papers (6)

1. How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals cs.LG · 2026 · author #1
2. Causal Evidence that Language Models use Confidence to Drive Behavior cs.LG · 2026 · author #1
3. How do LLMs Compute Verbal Confidence cs.CL · 2026 · author #1
4. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm cs.AI · 2017 · author #9
5. Learning to reinforcement learn cs.LG · 2016 · author #8
6. Learning to Navigate in Complex Environments cs.AI · 2016 · author #11

Mentions

• 2603.22161 #1 · arxiv_oai · confidence 0.70 Dharshan Kumaran
• 2603.17839 #1 · arxiv_oai · confidence 0.70 Dharshan Kumaran

Frequent Coauthors

• Petar Veli\v{c}kovi\'c 3 shared papers
• Simon Osindero 3 shared papers
• Viorica Patraucean 3 shared papers
• Hubert Soyer 2 shared papers
• Laurent Sifre 2 shared papers
• Nathaniel Daw 2 shared papers
• Andrea Banino 1 shared papers
• Andrew J. Ballard 1 shared papers
• Arthur Conmy 1 shared papers
• Arthur Guez 1 shared papers
• Charles Blundell 1 shared papers
• David Silver 1 shared papers
• Demis Hassabis 1 shared papers
• Dhruva Tirumala 1 shared papers
• Fabio Viola 1 shared papers
• Federico Barbero 1 shared papers
• Ioannis Antonoglou 1 shared papers
• Jane X Wang 1 shared papers
• Joel Z Leibo 1 shared papers
• Julian Schrittwieser 1 shared papers