English
Related papers

Related papers: Open Problems in Mechanistic Interpretability

200 papers

As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning. Studies in early MR have notably started inquiries into Explainable AI (XAI) -- arguably one of the biggest concerns today for…

Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in…

Machine Learning · Computer Science 2021-09-20 Guandong Xu , Tri Dung Duong , Qian Li , Shaowu Liu , Xianzhi Wang

Current speech translation systems, while having achieved impressive accuracies, are rather static in their behavior and do not adapt to real-world situations in ways human interpreters do. In order to improve their practical usefulness and…

Computation and Language · Computer Science 2025-08-12 Matthias Sperber , Maureen de Seyssel , Jiajun Bao , Matthias Paulik

Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power. In these applications, however, full automation is…

Human-Computer Interaction · Computer Science 2020-03-18 Vivian Lai , Samuel Carton , Chenhao Tan

There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by 'explainable' and…

Artificial Intelligence · Computer Science 2018-10-02 Alun Preece , Dan Harborne , Dave Braines , Richard Tomsett , Supriyo Chakraborty

Transformers have had a significant impact on natural language processing and have recently demonstrated their potential in computer vision. They have shown promising results over convolution neural networks in fundamental computer vision…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Rojina Kashefi , Leili Barekatain , Mohammad Sabokrou , Fatemeh Aghaeipoor

Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede…

Atmospheric and Oceanic Physics · Physics 2024-03-29 Ruyi Yang , Jingyu Hu , Zihao Li , Jianli Mu , Tingzhao Yu , Jiangjiang Xia , Xuhong Li , Aritra Dasgupta , Haoyi Xiong

The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on…

Machine Learning · Computer Science 2026-03-05 Elena Golimblevskaia , Aakriti Jain , Bruno Puri , Ammar Ibrahim , Wojciech Samek , Sebastian Lapuschkin

As machine learning (ML) systems take a more prominent and central role in contributing to life-impacting decisions, ensuring their trustworthiness and accountability is of utmost importance. Explanations sit at the core of these desirable…

Machine Learning · Computer Science 2021-06-16 Sahil Verma , Aditya Lahiri , John P. Dickerson , Su-In Lee

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the…

Artificial Intelligence · Computer Science 2020-06-23 Andrés Páez

Despite substantial efforts, neural network interpretability remains an elusive goal, with previous research failing to provide succinct explanations of most single neurons' impact on the network output. This limitation is due to the…

Machine Learning · Computer Science 2024-02-01 Simon C. Marshall , Jan H. Kirchner

The opaqueness of many complex machine learning algorithms is often mentioned as one of the main obstacles to the ethical development of artificial intelligence (AI). But what does it mean for an algorithm to be opaque? Highly complex…

Machine Learning · Computer Science 2025-08-20 Andrés Páez

The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black box" models, such as deep neural networks and ensemble methods. These models exhibit exceptional predictive performance, making them…

Machine Learning · Computer Science 2025-03-28 Moncef Garouani , Josiane Mothe , Ayah Barhrhouj , Julien Aligon

A common trait of many machine learning models is that it is often difficult to understand and explain what caused the model to produce the given output. While the explainability of neural networks has been an active field of research in…

The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods…

Machine Learning · Computer Science 2026-04-09 Stefan Haufe , Rick Wilming , Benedict Clark , Rustam Zhumagambetov , Ahcène Boubekki , Jörg Martin , Danny Panknin

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

Computation and Language · Computer Science 2024-04-17 Haiyan Zhao , Fan Yang , Bo Shen , Himabindu Lakkaraju , Mengnan Du

The lack of interpretability and transparency are preventing economists from using advanced tools like neural networks in their empirical research. In this paper, we propose a class of interpretable neural network models that can achieve…

Econometrics · Economics 2020-12-01 Yucheng Yang , Zhong Zheng , Weinan E

Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of…

Machine Learning · Statistics 2017-12-08 Fabian Offert

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

Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. This heightened focus stems from the widespread use of AI-backed systems. These systems, often relying on intricate neural…

Quantum Physics · Physics 2024-11-11 Lirandë Pira , Chris Ferrie