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

• URL: http://arxiv.org/abs/2604.08974v1
• Date: Fri, 10 Apr 2026 05:27:35 GMT
• Title: Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
• Abstract summary: We investigate the underlying behavior of confidence scores to understand its sensitivity to supervised fine-tuning.<n>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.<n>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.
• Score: 13.193737353434152
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning [5.094079537924077]
  We show that confidence trajectories separate correct from incorrect reasoning traces.<n> correctness-related information is enriched in the tail of reasoning.<n>We propose NeuralConf, a lightweight estimator that learns from confidence trajectories for correctness evaluation.
  arXiv  Detail & Related papers  (2026-05-16T05:57:00Z)
• BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents [58.05949210993854]
  We investigate whether search agents have the ability to communicate their own confidence through verbalized confidence scores after long sequences of actions.<n>We propose Test-Time Scaling (TTS) methods that use confidence scores to determine answer quality, encourage the model to try again until reaching a satisfactory confidence level.
  arXiv  Detail & Related papers  (2025-10-27T15:58:51Z)
• ADVICE: Answer-Dependent Verbalized Confidence Estimation [7.331438721730309]
  We conduct a detailed analysis of the dynamics underlying verbalized confidence.<n>We identify answer-independence as a key factor, defined as the model's failure to condition confidence on its own answer.<n>We propose a fine-tuning framework that facilitates answer-grounded confidence estimation.
  arXiv  Detail & Related papers  (2025-10-13T02:18:33Z)
• Calibrating Verbalized Confidence with Self-Generated Distractors [24.56911906044891]
  We introduce Distractor-Normalized Coherence (DINCO)<n>DINCO estimates and accounts for an LLM's suggestibility bias by having the model its confidence independently across several self-generated distractors.<n>We frame the popular approach of self-consistency as leveraging coherence across sampled generations, and normalized verbalized confidence as leveraging coherence across validations on incompatible claims.
  arXiv  Detail & Related papers  (2025-09-29T21:41:22Z)
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally [58.63318088243125]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare.<n>LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence"
  arXiv  Detail & Related papers  (2025-08-26T09:25:32Z)
• Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision [12.287123198288079]
  Uncertainty calibration is essential for the safe deployment of large language models (LLMs)<n>We find that supervised fine-tuning with scalar confidence labels alone suffices to elicit self-verification behavior of language models.<n>We propose a simple rethinking method that boosts performance via test-time scaling based on calibrated uncertainty.
  arXiv  Detail & Related papers  (2025-06-04T08:56:24Z)
• SteerConf: Steering LLMs for Confidence Elicitation [11.872504642312705]
  Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence.<n>We propose SteerConf, a novel framework that systematically steers LLMs' confidence scores to improve their calibration and reliability.
  arXiv  Detail & Related papers  (2025-03-04T18:40:49Z)
• Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences [62.52739672949452]
  Language models (LMs) should provide reliable confidence estimates to help users detect mistakes in their outputs and defer to human experts when necessary.<n>We propose relative confidence estimation, where we match up questions against each other and ask the model to make relative judgments of confidence.<n>Treating each question as a "player" in a series of matchups against other questions and the model's preferences as match outcomes, we can use rank aggregation methods like Elo rating and Bradley-Terry to translate the model's confidence preferences into confidence scores.
  arXiv  Detail & Related papers  (2025-02-03T07:43:27Z)
• Confidence in the Reasoning of Large Language Models [0.0]
  Confidence is measured in terms of persistence in keeping their answer when prompted to reconsider.<n> Confidence is only partially explained by the underlying token-level probability.
  arXiv  Detail & Related papers  (2024-12-19T10:04:29Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Did You Mean...? Confidence-based Trade-offs in Semantic Parsing [52.28988386710333]
  We show how a calibrated model can help balance common trade-offs in task-oriented parsing. We then examine how confidence scores can help optimize the trade-off between usability and safety.
  arXiv  Detail & Related papers  (2023-03-29T17:07:26Z)
• An evaluation of word-level confidence estimation for end-to-end automatic speech recognition [70.61280174637913]
  We investigate confidence estimation for end-to-end automatic speech recognition (ASR) We provide an extensive benchmark of popular confidence methods on four well-known speech datasets. Our results suggest a strong baseline can be obtained by scaling the logits by a learnt temperature.
  arXiv  Detail & Related papers  (2021-01-14T09:51:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.