Believe Your Model: Distribution-Guided Confidence Calibration

• URL: http://arxiv.org/abs/2603.03872v1
• Date: Wed, 04 Mar 2026 09:25:36 GMT
• Title: Believe Your Model: Distribution-Guided Confidence Calibration
• Authors: Xizhong Yang, Haotian Zhang, Huiming Wang, Mofei Song,
• Abstract summary: Internal model signals like confidence scores can partly indicate response correctness and exhibit a distributional correlation with accuracy.<n>We propose DistriVoting, which incorporates distributional priors as another signal alongside confidence during voting.<n>Our method significantly outperforms state-of-the-art approaches.
• Score: 21.158022185490424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple candidate responses and selecting the most reliable answer. While prior work has analyzed that internal model signals like confidence scores can partly indicate response correctness and exhibit a distributional correlation with accuracy, such distributional information has not been fully utilized to guide answer selection. Motivated by this, we propose DistriVoting, which incorporates distributional priors as another signal alongside confidence during voting. Specifically, our method (1) first decomposes the mixed confidence distribution into positive and negative components using Gaussian Mixture Models, (2) then applies a reject filter based on positive/negative samples from them to mitigate overlap between the two distributions. Besides, to further alleviate the overlap from the perspective of distribution itself, we propose SelfStepConf, which uses step-level confidence to dynamically adjust inference process, increasing the separation between the two distributions to improve the reliability of confidences in voting. Experiments across 16 models and 5 benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches.

Related papers

• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings [23.3862001690226]
  Estimating the distribution of outcomes under counterfactual policies is critical for decision-making in domains such as recommendation, advertising, and healthcare.<n>We propose and analyze a novel framework-Counterfactual Policy Mean Embedding (CPME)-that represents the entire counterfactual outcome distribution in a reproducing kernel space (RKHS)<n>We introduce both a plug-in estimator and a doubly robust estimator; the latter enjoys improved convergence rates by correcting for bias in both the outcome embedding and propensity models.
  arXiv  Detail & Related papers  (2025-06-03T12:16:46Z)
• Graph-based Confidence Calibration for Large Language Models [22.394717844099684]
  We propose using an auxiliary learning model to assess response correctness based on the self-consistency of multiple outputs generated by the large language models.<n>Our method builds a consistency graph to represent the agreement among multiple responses and uses a graph neural network (GNN) to estimate the likelihood that each response is correct.
  arXiv  Detail & Related papers  (2024-11-03T20:36:44Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
  This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models. We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
  arXiv  Detail & Related papers  (2023-11-03T05:41:25Z)
• Towards Better Certified Segmentation via Diffusion Models [62.21617614504225]
  segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-decision systems like healthcare or autonomous driving. Recently, randomized smoothing has been proposed to certify segmentation predictions by adding Gaussian noise to the input to obtain theoretical guarantees. In this paper, we address the problem of certifying segmentation prediction using a combination of randomized smoothing and diffusion models.
  arXiv  Detail & Related papers  (2023-06-16T16:30:39Z)
• Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation [30.34223543030105]
  We show how NeighborAgg can leverage the two essential information via an adaptive neighborhood aggregation. We also extend our approach to the closely related task of mislabel detection and provide a theoretical coverage guarantee to bound the false negative.
  arXiv  Detail & Related papers  (2022-11-29T18:43:15Z)
• Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier [11.233334009240947]
  A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. This paper proposes an application of counterfactual explanations in fixing an over-confident classifier.
  arXiv  Detail & Related papers  (2022-10-21T18:53:16Z)
• SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness [61.212486108346695]
  We propose a training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified $ell$-robustness of smoothed classifiers.
  arXiv  Detail & Related papers  (2021-11-17T18:20:59Z)
• Binary Classification from Positive Data with Skewed Confidence [85.18941440826309]
  Positive-confidence (Pconf) classification is a promising weakly-supervised learning method. In practice, the confidence may be skewed by bias arising in an annotation process. We introduce the parameterized model of the skewed confidence, and propose the method for selecting the hyper parameter.
  arXiv  Detail & Related papers  (2020-01-29T00:04:36Z)

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.