Skip to content
conftrace_
2025 ICML ICML 2025

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Jiancong Xiao, Bojian Hou, Zhanliang Wang, Ruochen Jin, Qi Long, Weijie J Su, Li Shen

Topics

Natural Language Processing > Resources & Methods > Large Language Models Artificial Intelligence > Core AI > Large Language Models

Keywords

calibration em algorithm expected calibration error fine tuning alignment overconfidence
Download PDF