# On the Performance of Concept Probing: The Influence of the Data (Extended Version)

Source: [On the Performance of Concept Probing: The Influence of the Data (Extended Version)](<https://www.sota2.com/research/paper/68fa7a351e209131cea81cac>)

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

Data updated: 2025-10-28T13:57:19.505Z

Authors: Manuel de Sousa Ribeiro, Afonso Leote, Jo\\~ao Leite

Published: 2025-07-24T16:18:46.000Z

## Abstract

Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct human interpretation. Concept probing works by training additional classifiers to map the internal representations of a model into human-defined concepts of interest, thus allowing humans to peek inside artificial neural networks. Research on concept probing has mainly focused on the model being probed or the probing model itself, paying limited attention to the data required to train such probing models. In this paper, we address this gap. Focusing on concept probing in the context of image classification tasks, we investigate the effect of the data used to train probing models on their performance. We also make available concept labels for two widely used datasets.

## 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/2507.18550>)

[PDF](<https://arxiv.org/pdf/2507.18550.pdf>)