English
Related papers

Related papers: Obtaining Faithful Interpretations from Compositio…

200 papers

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed…

Machine Learning · Computer Science 2025-05-30 Chang Yue , Niraj K. Jha

Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not…

Machine Learning · Computer Science 2023-03-10 Han Xuanyuan , Pietro Barbiero , Dobrik Georgiev , Lucie Charlotte Magister , Pietro Lió

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yunhao Ge , Yao Xiao , Zhi Xu , Meng Zheng , Srikrishna Karanam , Terrence Chen , Laurent Itti , Ziyan Wu

Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…

Machine Learning · Computer Science 2020-12-07 Adam Noack , Isaac Ahern , Dejing Dou , Boyang Li

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…

Computation and Language · Computer Science 2022-12-08 Wanjun Zhong , Tingting Ma , Jiahai Wang , Jian Yin , Tiejun Zhao , Chin-Yew Lin , Nan Duan

As artificial intelligence increasingly drives critical decisions, the ability to genuinely explain how neural networks make predictions is essential for trust. Yet, most current explanation methods offer post-hoc rationalizations rather…

Machine Learning · Computer Science 2026-05-08 Corentin Lobet , Francesca Chiaromonte

Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP can acquire this ability while learning from data is an open question. In this paper,…

Computation and Language · Computer Science 2023-08-02 Josef Valvoda , Naomi Saphra , Jonathan Rawski , Adina Williams , Ryan Cotterell

Artificial neural networks (ANNs), inspired by the interconnection of real neurons, have achieved unprecedented success in various fields such as computer vision and natural language processing. Recently, a novel mathematical ANN model,…

Neural and Evolutionary Computing · Computer Science 2023-09-15 Yu Ding , Jun Yu , Chunzhi Gu , Shangce Gao , Chao Zhang

Interpreting the prediction mechanism of complex models is currently one of the most important tasks in the machine learning field, especially with layered neural networks, which have achieved high predictive performance with various…

Machine Learning · Statistics 2018-10-04 Chihiro Watanabe

In many settings it is important for one to be able to understand why a model made a particular prediction. In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet…

Computation and Language · Computer Science 2020-05-04 Sarthak Jain , Sarah Wiegreffe , Yuval Pinter , Byron C. Wallace

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

Machine Learning · Computer Science 2024-01-08 Shun Liu

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are…

Computation and Language · Computer Science 2023-07-03 Pepa Atanasova , Oana-Maria Camburu , Christina Lioma , Thomas Lukasiewicz , Jakob Grue Simonsen , Isabelle Augenstein

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…

Machine Learning · Computer Science 2021-11-04 Miles Q. Li , Benjamin C. M. Fung , Adel Abusitta

Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks…

Atmospheric and Oceanic Physics · Physics 2020-10-28 Benjamin A. Toms , Elizabeth A. Barnes , Imme Ebert-Uphoff

Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic sentence embedding…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Daqing Liu , Hanwang Zhang , Feng Wu , Zheng-Jun Zha

While a real-world research program in mathematics may be guided by a motivating question, the process of mathematical discovery is typically open-ended. Ideally, exploration needed to answer the original question will reveal new…

Machine Learning · Computer Science 2026-01-30 Henry Kvinge , Andrew Aguilar , Nayda Farnsworth , Grace O'Brien , Robert Jasper , Sarah Scullen , Helen Jenne

Machine learning-based methods have achieved successful applications in machinery fault diagnosis. However, the main limitation that exists for these methods is that they operate as a black box and are generally not interpretable. This…

Machine Learning · Computer Science 2022-04-20 Gang Chen , Yu Lu , Rong Su , Zhaodan Kong

Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing models did not make full use of the unique structural…

Software Engineering · Computer Science 2021-04-02 Wenhan Wang , Ge Li , Sijie Shen , Xin Xia , Zhi Jin

Attention mechanisms have seen wide adoption in neural NLP models. In addition to improving predictive performance, these are often touted as affording transparency: models equipped with attention provide a distribution over attended-to…

Computation and Language · Computer Science 2019-05-10 Sarthak Jain , Byron C. Wallace