English
Related papers

Related papers: Concept-Based Mechanistic Interpretability Using S…

200 papers

We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of…

Machine Learning · Computer Science 2024-02-20 Jonas Teufel , Luca Torresi , Patrick Reiser , Pascal Friederich

Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains. This paradigm aims to provide attribution to components of neural systems where…

Information Retrieval · Computer Science 2025-01-20 Andrew Parry , Catherine Chen , Carsten Eickhoff , Sean MacAvaney

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…

Machine Learning · Computer Science 2025-02-20 Or Raphael Bidusa , Shaul Markovitch

The lack of transparency in the decision-making processes of deep learning systems presents a significant challenge in modern artificial intelligence (AI), as it impairs users' ability to rely on and verify these systems. To address this…

Artificial Intelligence · Computer Science 2024-11-18 David Debot , Pietro Barbiero , Francesco Giannini , Gabriele Ciravegna , Michelangelo Diligenti , Giuseppe Marra

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Jayneel Parekh , Quentin Bouniot , Pavlo Mozharovskyi , Alasdair Newson , Florence d'Alché-Buc

Explainability of Deep Neural Networks (DNNs) has been garnering increasing attention in recent years. Of the various explainability approaches, concept-based techniques stand out for their ability to utilize human-meaningful concepts…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Fatemeh Aghaeipoor , Dorsa Asgarian , Mohammad Sabokrou

This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm…

Computation and Language · Computer Science 2025-08-21 Wuyang Zhang , Yexin Tian , Xiandong Meng , Mengjie Wang , Junliang Du

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Machine Learning · Computer Science 2026-05-12 Ward Gauderis , Thomas Dooms , Steven T. Holmer , Kola Ayonrinde , Geraint A. Wiggins

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

Machine Learning · Computer Science 2025-12-01 Angela van Sprang , Erman Acar , Willem Zuidema

Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to rely on and verify state-of-the-art DNN-based systems,…

Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding neurons into the…

Machine Learning · Computer Science 2022-11-16 Wei Han , Yangqiming Wang , Christian Böhm , Junming Shao

The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanations extracted from the latent representations obtained after…

Machine Learning · Computer Science 2026-04-23 Lucie Charlotte Magister , Pietro Lio

Concept-based Models are a class of inherently explainable networks that improve upon standard Deep Neural Networks by providing a rationale behind their predictions using human-understandable `concepts'. With these models being highly…

Machine Learning · Computer Science 2025-06-06 Sanchit Sinha , Aidong Zhang

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Haifei Zhang , Patrick Barry , Eduardo Brandao

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which…

Computation and Language · Computer Science 2019-09-06 Bill Yuchen Lin , Xinyue Chen , Jamin Chen , Xiang Ren

The emergence of explainability methods has enabled a better comprehension of how deep neural networks operate through concepts that are easily understood and implemented by the end user. While most explainability methods have been designed…

Neurons and Cognition · Quantitative Biology 2022-03-17 Fernanda L. Ribeiro , Steffen Bollmann , Ross Cunnington , Alexander M. Puckett

Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits…

Machine Learning · Computer Science 2025-08-22 Sebastian Musiał , Bartosz Zieliński , Tomasz Danel

Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to…

Machine Learning · Computer Science 2023-06-21 Ola Ahmad , Nicolas Bereux , Loïc Baret , Vahid Hashemi , Freddy Lecue

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Computation and Language · Computer Science 2023-08-29 Vedant Palit , Rohan Pandey , Aryaman Arora , Paul Pu Liang