Reinforcement Learning with Metacognitive Feedback Elicits Uncertainty in LLMs(arxiv.org)
arxiv.org
Reinforcement Learning with Metacognitive Feedback Elicits Uncertainty in LLMs
https://arxiv.org/abs/2606.32032
1 comments
> Since monitoring task performance
and adapting behavior accordingly are central to metacognition, we posit that mod-
els capable of accurately judging their own performance are better positioned to
improve it. We operationalize this idea via two novel mechanisms: reinforcement
learning with metacognitive feedback (RLMF), a paradigm to refine completion
rankings during preference optimization based on the quality of a model’s self-
judgments of performance, and metacognitive data selection, which uses similar
self-judgments to identify high-value training examples, outperforming naive active
learning.