Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ribeiro, Manuel de Sousa, Leote, Afonso, Leite, João
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.18550
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913959039205376
author Ribeiro, Manuel de Sousa
Leote, Afonso
Leite, João
author_facet Ribeiro, Manuel de Sousa
Leote, Afonso
Leite, João
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18550
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Performance of Concept Probing: The Influence of the Data (Extended Version)
Ribeiro, Manuel de Sousa
Leote, Afonso
Leite, João
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
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.
title On the Performance of Concept Probing: The Influence of the Data (Extended Version)
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2507.18550