English
Related papers

Related papers: Learning Interpretable Concept-Based Models with H…

200 papers

How do classification models "see" our data? Based on their success in delineating behaviors, there must be some lens through which it is easy to see the boundary between classes; however, our current set of visualization techniques makes…

Machine Learning · Computer Science 2026-03-17 Christian Jorgensen , Arthur Y. Lin , Rhushil Vasavada , Rose K. Cersonsky

How can we find interpretable, domain-appropriate models of natural phenomena given some complex, raw data such as images? Can we use such models to derive scientific insight from the data? In this paper, we propose some methods for…

Machine Learning · Computer Science 2024-02-06 Christopher J. Soelistyo , Alan R. Lowe

Understanding complex machine learning models such as deep neural networks with explanations is crucial in various applications. Many explanations stem from the model perspective, and may not necessarily effectively communicate why the…

Machine Learning · Computer Science 2022-02-28 Chih-Kuan Yeh , Been Kim , Pradeep Ravikumar

In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Yan Cui , Shuhong Liu , Liuzhuozheng Li , Zhiyuan Yuan

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

Machine learning models are trained with relatively simple objectives, such as next token prediction. However, on deployment, they appear to capture a more fundamental representation of their input data. It is of interest to understand the…

Machine Learning · Computer Science 2024-12-23 Thomas Walker

Concept Bottleneck Models (CBMs) assume that training examples (e.g., x-ray images) are annotated with high-level concepts (e.g., types of abnormalities), and perform classification by first predicting the concepts, followed by predicting…

Computation and Language · Computer Science 2023-12-19 Danis Alukaev , Semen Kiselev , Ilya Pershin , Bulat Ibragimov , Vladimir Ivanov , Alexey Kornaev , Ivan Titov

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features. Even simple, highly interpretable model types such…

Machine Learning · Computer Science 2022-02-25 Alexandra Zytek , Ignacio Arnaldo , Dongyu Liu , Laure Berti-Equille , Kalyan Veeramachaneni

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Machine Learning · Computer Science 2021-02-03 Andrew Slavin Ross , Nina Chen , Elisa Zhao Hang , Elena L. Glassman , Finale Doshi-Velez

Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing. When no human concept labels are available, concept discovery methods search trained embedding spaces for interpretable…

Machine Learning · Statistics 2023-06-07 Tobias Leemann , Michael Kirchhof , Yao Rong , Enkelejda Kasneci , Gjergji Kasneci

Many text classification applications require models with satisfying performance as well as good interpretability. Traditional machine learning methods are easy to interpret but have low accuracies. The development of deep learning models…

Computation and Language · Computer Science 2020-06-02 Zhengyang Wang , Xia Hu , Shuiwang Ji

Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees,…

Machine Learning · Computer Science 2019-06-13 Owen Lahav , Nicholas Mastronarde , Mihaela van der Schaar

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Hila Chefer , Oran Lang , Mor Geva , Volodymyr Polosukhin , Assaf Shocher , Michal Irani , Inbar Mosseri , Lior Wolf

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

Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop. Previous work has focused on providing concepts for specific models (eg, neural networks) or data types (eg, images), and by either…

Machine Learning · Computer Science 2022-05-10 João Bento Sousa , Ricardo Moreira , Vladimir Balayan , Pedro Saleiro , Pedro Bizarro

The goal of model distillation is to faithfully transfer teacher model knowledge to a model which is faster, more generalizable, more interpretable, or possesses other desirable characteristics. Human-readability is an important and…

Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of…

Computation and Language · Computer Science 2020-05-01 Hiroki Ouchi , Jun Suzuki , Sosuke Kobayashi , Sho Yokoi , Tatsuki Kuribayashi , Ryuto Konno , Kentaro Inui

Recent efforts to learn reward functions from human feedback have tended to use deep neural networks, whose lack of transparency hampers our ability to explain agent behaviour or verify alignment. We explore the merits of learning…

Machine Learning · Computer Science 2022-10-04 Tom Bewley , Jonathan Lawry , Arthur Richards , Rachel Craddock , Ian Henderson

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

Machine Learning · Statistics 2020-06-22 Michael Tsang , Sirisha Rambhatla , Yan Liu

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI…

Machine Learning · Computer Science 2024-01-05 Tim Räz