# Prior Distribution and Model Confidence

Source: [Prior Distribution and Model Confidence](<https://www.sota2.com/research/paper/68fa7b2d1e209131cea870ce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-29T05:00:05.135Z

Authors: Maksim Kazanskii, Artem Kasianov

Published: 2025-09-05T20:17:26.000Z

## Abstract

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test samples from the training distribution in embedding space, without requiring retraining. By filtering low-density (low-confidence) predictions, our method significantly improves classification accuracy. We evaluate Embedding Density across multiple architectures and compare it with state-of-the-art out-of-distribution (OOD) detection methods. The proposed approach is potentially generalizable beyond computer vision.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.05485>)

[PDF](<https://arxiv.org/pdf/2509.05485.pdf>)