English
Related papers

Related papers: A Causal Lens for Peeking into Black Box Predictiv…

200 papers

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad…

Machine Learning · Computer Science 2025-05-20 Yizuo Chen , Amit Bhatia

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

Machine Learning · Computer Science 2018-03-14 Osbert Bastani , Carolyn Kim , Hamsa Bastani

We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference. Interpretability is paramount in…

Methodology · Statistics 2023-04-05 Marco Morucci , Cynthia Rudin , Alexander Volfovsky

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

The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods,…

Machine Learning · Computer Science 2024-10-29 Yihao Zhang

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a…

Machine Learning · Computer Science 2020-10-23 Matthew O'Shaughnessy , Gregory Canal , Marissa Connor , Mark Davenport , Christopher Rozell

Causal inference is often portrayed as fundamentally distinct from predictive modeling, with its own terminology, goals, and intellectual challenges. But at its core, causal inference is simply a structured instance of prediction under…

Machine Learning · Computer Science 2025-07-10 Carlos Fernández-Loría

Explaining the decisions of black-box models is a central theme in the study of trustworthy ML. Numerous measures have been proposed in the literature; however, none of them take an axiomatic approach to causal explainability. In this work,…

Machine Learning · Computer Science 2024-02-20 Gagan Biradar , Vignesh Viswanathan , Yair Zick

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Artificial Intelligence · Computer Science 2026-05-22 Hengrui Cai , Shengjie Liu , Rui Song

Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for…

Machine Learning · Statistics 2019-09-24 Cynthia Rudin

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…

We present an interpretable companion model for any pre-trained black-box classifiers. The idea is that for any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or…

Machine Learning · Statistics 2020-02-12 Danqing Pan , Tong Wang , Satoshi Hara

As predictive models -- e.g., from machine learning -- give likely outcomes, they may be used to reason on the effect of an intervention, a causal-inference task. The increasing complexity of health data has opened the door to a plethora of…

Machine Learning · Statistics 2023-05-17 Matthieu Doutreligne , Gaël Varoquaux

Black box models in machine learning have demonstrated excellent predictive performance in complex problems and high-dimensional settings. However, their lack of transparency and interpretability restrict the applicability of such models in…

Machine Learning · Computer Science 2020-06-09 Numair Sani , Jaron Lee , Razieh Nabi , Ilya Shpitser

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably…

Machine Learning · Computer Science 2019-02-12 Brandon Carter , Jonas Mueller , Siddhartha Jain , David Gifford

The goal of causal inference is to understand the outcome of alternative courses of action. However, all causal inference requires assumptions. Such assumptions can be more influential than in typical tasks for probabilistic modeling, and…

Methodology · Statistics 2016-10-31 Dustin Tran , Francisco J. R. Ruiz , Susan Athey , David M. Blei

The use of sophisticated machine learning models for critical decision making is faced with a challenge that these models are often applied as a "black-box". This has led to an increased interest in interpretable machine learning, where…

Artificial Intelligence · Computer Science 2020-07-22 Catarina Moreira , Yu-Liang Chou , Mythreyi Velmurugan , Chun Ouyang , Renuka Sindhgatta , Peter Bruza

The standard approach to causal modelling especially in social and health sciences is the potential outcomes framework due to Neyman and Rubin. In this framework, observations are thought to be drawn from a distribution over variables of…

Methodology · Statistics 2025-07-18 Benedikt Höltgen , Robert C. Williamson

Most major retailers today have multiple divisions focused on various aspects, such as marketing, supply chain, online customer experience, store customer experience, employee productivity, and vendor fulfillment. They also regularly…

Machine Learning · Computer Science 2025-12-16 Pranav Gupta , Nithin Surendran