cs.NEFeb 2, 2026

Fine-Tuning Language Models to Know What They Know

Authors: Sangjun Park, Elliot Meyerson, Xin Qiu, Risto Miikkulainen

Organizations: The University of Texas at Austin · Cognizant AI Lab

Abstract

Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using the dtype2′d'_{\rm type2} metric is established to isolate metacognitive ability. The Evolution Strategy for Metacognitive Alignment (ESMA) is proposed, demonstrating robust generalization across unseen datasets, languages, and newly acquired knowledge. Gradual parameter updates reveal that these improvements are driven by a sparse set of parameters, opening a potential avenue for targeted metacognitive optimization.

Figures & tables

Appendix figures & tables28 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Metacognition in LLMs: Foundations, Progress, and Opportunities

    Jul 13, 2026Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu +3Language Model Self-AssessmentMetacognition in Language Models

  2. LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling

    May 13, 2026Qi Cao, Yufan Wang, Peijia Qin +2LLM InferenceTest-Time Scaling