Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation

2026-04-09

AI Summary

This work addresses the widespread lack of reliable confidence estimation in pretrained models and the high computational cost and poor compatibility of existing uncertainty quantification methods. To overcome these limitations, the authors propose ETN, a lightweight post-processing module that applies sample-dependent affine transformations in logit space and interprets the transformed outputs as parameters of a Dirichlet distribution. This approach enables, for the first time, the conversion of any pretrained model into an evidential model without retraining. Evaluated on both image classification and large language model question-answering tasks, ETN significantly outperforms existing post-hoc baselines in uncertainty estimation quality under both in-distribution and out-of-distribution settings, while introducing negligible computational overhead—thus achieving an effective balance among accuracy, efficiency, and deployment practicality.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncertainty estimation methods, such as deep ensembles and MC dropout, are often too computationally expensive to deploy in practice. Evidential Deep Learning (EDL) offers a more efficient alternative, but it requires models to be trained to output evidential quantities from the start, which is rarely true for pretrained networks. To enable EDL-style uncertainty estimation in pretrained models, we propose the Evidential Transformation Network (ETN), a lightweight post-hoc module that converts a pretrained predictor into an evidential model. ETN operates in logit space: it learns a sample-dependent affine transformation of the logits and interprets the transformed outputs as parameters of a Dirichlet distribution for uncertainty estimation. We evaluate ETN on image classification and large language model question-answering benchmarks under both in-distribution and out-of-distribution settings. ETN consistently improves uncertainty estimation over post-hoc baselines while preserving accuracy and adding only minimal computational overhead.

Problem

• uncertainty estimation
• pretrained models
• evidential deep learning
• post-hoc calibration
• computational efficiency

Innovation

• Evidential Deep Learning
• Uncertainty Estimation
• Post-hoc Calibration
• Dirichlet Distribution
• Pretrained Models