Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
On calibration of modern neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
citing papers explorer
-
Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
- Process Supervision of Confidence Margin for Calibrated LLM Reasoning