Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flores, Lorenzo Jaime Yu, di-Piano, Cesare Spinoso, Cheung, Jackie Chi Kit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908951256236032
author Flores, Lorenzo Jaime Yu
di-Piano, Cesare Spinoso
Cheung, Jackie Chi Kit
author_facet Flores, Lorenzo Jaime Yu
di-Piano, Cesare Spinoso
Cheung, Jackie Chi Kit
contents Uncertainty quantification is a set of techniques that measure confidence in language models. They can be used, for example, to detect hallucinations or alert users to review uncertain predictions. To be useful, these confidence scores must be correlated with the quality of the output. However, recent work found that fine-tuning can affect the correlation between confidence scores and quality. Hence, we investigate the underlying behavior of confidence scores to understand its sensitivity to supervised fine-tuning (SFT). We find that post-SFT, the correlation of various confidence scores degrades, which can stem from changes in confidence scores due to factors other than the output quality, such as the output's similarity to the training distribution. We demonstrate via a case study how failing to address this miscorrelation reduces the usefulness of the confidence scores on a downstream task. Our findings show how confidence metrics cannot be used off-the-shelf without testing, and motivate the need for developing metrics which are more robust to fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08974
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Flores, Lorenzo Jaime Yu
di-Piano, Cesare Spinoso
Cheung, Jackie Chi Kit
Computation and Language
Uncertainty quantification is a set of techniques that measure confidence in language models. They can be used, for example, to detect hallucinations or alert users to review uncertain predictions. To be useful, these confidence scores must be correlated with the quality of the output. However, recent work found that fine-tuning can affect the correlation between confidence scores and quality. Hence, we investigate the underlying behavior of confidence scores to understand its sensitivity to supervised fine-tuning (SFT). We find that post-SFT, the correlation of various confidence scores degrades, which can stem from changes in confidence scores due to factors other than the output quality, such as the output's similarity to the training distribution. We demonstrate via a case study how failing to address this miscorrelation reduces the usefulness of the confidence scores on a downstream task. Our findings show how confidence metrics cannot be used off-the-shelf without testing, and motivate the need for developing metrics which are more robust to fine-tuning.
title Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
topic Computation and Language
url https://arxiv.org/abs/2604.08974