FIELD NOTES TOPIC
metacognitive feedback
1 note, newest first.
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
The paper discusses a new approach called Reinforcement Learning with Metacognitive Feedback (RLMF) to improve Language Model's (LLM) metacognitive abilities. The RLMF aims to help LLMs better monitor and regulate…
