English
Related papers

Related papers: Open Problems in Mechanistic Interpretability

200 papers

Interpretable insights from predictive models remain critical in bio-statistics, particularly when assessing causality, where classical statistical and machine learning methods often provide inherent clarity. While Neural Networks (NNs)…

Applications · Statistics 2025-05-02 Jean-Baptiste A. Conan

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…

Machine Learning · Computer Science 2022-05-02 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting. Since both provide information about predictors and…

Machine Learning · Computer Science 2024-04-26 Benjamin Leblanc , Pascal Germain

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to…

Artificial Intelligence · Computer Science 2025-01-28 David J. Chalmers

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid…

Image and Video Processing · Electrical Eng. & Systems 2021-11-05 Zohaib Salahuddin , Henry C Woodruff , Avishek Chatterjee , Philippe Lambin

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

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this…

Machine Learning · Computer Science 2021-09-02 Cynthia Rudin , Chaofan Chen , Zhi Chen , Haiyang Huang , Lesia Semenova , Chudi Zhong

The lack of interpretability has hindered the large-scale adoption of AI technologies. However, the fundamental idea of interpretability, as well as how to put it into practice, remains unclear. We provide notions of interpretability based…

Machine Learning · Computer Science 2021-11-18 Hangcheng Dong , Bingguo Liu , Fengdong Chen , Dong Ye , Guodong Liu

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other…

Machine Learning · Statistics 2017-03-06 Finale Doshi-Velez , Been Kim

The term "interpretability" is oftenly used by machine learning researchers each with their own intuitive understanding of it. There is no universal well agreed upon definition of interpretability in machine learning. As any type of science…

Machine Learning · Computer Science 2018-07-26 Abdul Karim , Avinash Mishra , MA Hakim Newton , Abdul Sattar

In machine learning (ML), it is in general challenging to provide a detailed explanation on how a trained model arrives at its prediction. Thus, usually we are left with a black-box, which from a scientific standpoint is not satisfactory.…

Materials Science · Physics 2021-04-22 Luca M. Ghiringhelli

Interpretability of machine learning models has gained more and more attention among researchers in the artificial intelligence (AI) and human-computer interaction (HCI) communities. Most existing work focuses on decision making, whereas we…

Human-Computer Interaction · Computer Science 2020-04-16 Haizi Yu , Heinrich Taube , James A. Evans , Lav R. Varshney

Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized into post-hoc methods and…

Machine Learning · Computer Science 2021-06-25 Sandareka Wickramanayake , Wynne Hsu , Mong Li Lee

There is a need of ensuring machine learning models that are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end-users. Further, interpretable machine learning models…

Machine Learning · Computer Science 2020-08-17 Gregor Stiglic , Primoz Kocbek , Nino Fijacko , Marinka Zitnik , Katrien Verbert , Leona Cilar

There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought…

Artificial Intelligence · Computer Science 2019-02-05 Leilani H. Gilpin , David Bau , Ben Z. Yuan , Ayesha Bajwa , Michael Specter , Lalana Kagal

Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known, but opaque low-level details of black box AI…

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a…

Machine Learning · Computer Science 2021-03-05 Michael Tsang , James Enouen , Yan Liu

Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks. Surpassing…

Artificial Intelligence · Computer Science 2021-05-19 Gargi Joshi , Rahee Walambe , Ketan Kotecha