From the 1 of 5 linked papers with an AI index.
5 papers
The Computational Basis of Confidence in Large Language Models
Dharshan Kumaran, Viorica Patraucean, Maks Ovsjanikov +3
The paper investigates what the confidence signal in large language models actually represents, showing that answer logits often act as monotonic readouts of a latent decision vari…
Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist
Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby +5
Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approa…
ATLAS: Active Theory Learning for Automated Science
Noémi ÃltetÅ, Nathaniel D. Daw, Kimberly L. Stachenfeld +1
Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit withi…
Causal Evidence that Language Models use Confidence to Drive Behavior
Dharshan Kumaran, Nathaniel Daw, Simon Osindero +2
Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstrates that confidence signals can…
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
Dharshan Kumaran, Viorica Patraucean, Simon Osindero +2
Large language models can detect their own errors and sometimes correct them without external feedback, but the underlying mechanisms remain unknown. We investigate this through th…