Research
Feeling of Knowing in Large Language Models
This paper introduces a functional 'feeling of knowing' (FoK) mechanism for LLMs to align answerability judgments with post-training knowledge updates. It proposes two trainable channels—knowledge and FoK—trained via three stages: on-policy supervised fine-tuning, knowledge-delta FoK training, and FoK-guided policy optimization. Experiments on factual QA and sequential updates show improved judgment quality without sacrificing capability on MMLU and ARC-Easy.
LLM alignmentknowledge judgmentmodel routing