From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty

Azza Jenane, Nassim Walha, Lukas Kuhn, Florian Buettner
January 2026
Cite DOI URL
Type
Conference paper
Publication
Proceedings of the AISTATS 2026 Workshop: Towards Trustworthy Predictions: Theory and Applications of Calibration for Modern AI
Azza Jenane
Azza Jenane
Ph.D. Candidate
Nassim Walha
Nassim Walha
Ph.D. Candidate
Lukas Kuhn
Lukas Kuhn
Staff Scientist
Florian Buettner
Florian Buettner
Professor for Bioinformatics in Oncology