Dharshan Kumaran
@dharshsky
Neuroscientist → ML researcher @ DeepMind · LLMs, Metacognition, confidence · Chess GM · London
135 Following 187 Followers
Do LLMs passively report confidence—or do they use it to guide behaviour? Our @NatMachIntell paper provides causal evidence for the latter: boosting/suppressing confidence changes whether models answer or abstain. Open access: @GoogleDeepMind @Princeton
Show more
Are LLMs stubborn or oversensitive to pushback? Both—at once. Our new @NatMachIntell paper helps us understand why LLMs become more confident in their initial answers, and how they markedly overweight opposing advice. Open access at: @GoogleDeepMind × @UCL_ICN
Show more
