LLMs have linearly decodable functional metacognitive states that causally modulate reasoning when steered via activation interventions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Decomposing and Steering Functional Metacognition in Large Language Models
LLMs have linearly decodable functional metacognitive states that causally modulate reasoning when steered via activation interventions.