English
Related papers

Related papers: Modeling Discrimination with Causal Abstraction

200 papers

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Computation and Language · Computer Science 2021-12-13 Lei Ding , Dengdeng Yu , Jinhan Xie , Wenxing Guo , Shenggang Hu , Meichen Liu , Linglong Kong , Hongsheng Dai , Yanchun Bao , Bei Jiang

This paper introduces a novel decomposition framework to explain heterogeneity in causal effects observed across different studies, considering both observational and randomized settings. We present a formal decomposition of between-study…

Methodology · Statistics 2025-12-18 Brian Gilbert , Ivan Dıaz , Kara E. Rudolph , Nicholas Williams , Tat-Thang Vo

Machine learning based systems are reaching society at large and in many aspects of everyday life. This phenomenon has been accompanied by concerns about the ethical issues that may arise from the adoption of these technologies. ML fairness…

Machine Learning · Computer Science 2021-01-01 Luca Oneto , Silvia Chiappa

Counterfactual fairness alleviates the discrimination between the model prediction toward an individual in the actual world (observational data) and that in counterfactual world (i.e., what if the individual belongs to other sensitive…

Machine Learning · Computer Science 2023-03-28 Tri Dung Duong , Qian Li , Guandong Xu

Fairness of machine learning models in healthcare has drawn increasing attention from clinicians, researchers, and even at the highest level of government. On the other hand, the importance of developing and deploying interpretable or…

Machine Learning · Computer Science 2024-09-04 Mary M. Lucas , Xiaoyang Wang , Chia-Hsuan Chang , Christopher C. Yang , Jacqueline E. Braughton , Quyen M. Ngo

Causal models with unobserved variables impose nontrivial constraints on the distributions over the observed variables. When a common cause of two variables is unobserved, it is impossible to uncover the causal relation between them without…

Statistics Theory · Mathematics 2021-12-14 Beata Zjawin , Elie Wolfe , Robert W. Spekkens

Decision-making systems based on AI and machine learning have been used throughout a wide range of real-world scenarios, including healthcare, law enforcement, education, and finance. It is no longer far-fetched to envision a future where…

Artificial Intelligence · Computer Science 2022-07-26 Drago Plecko , Elias Bareinboim

Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mitigate its effects,…

Machine Learning · Computer Science 2020-02-19 John Miller , Smitha Milli , Moritz Hardt

The aim of this paper is to make clear and precise the relationship between the Rubin causal model (RCM) and structural causal model (SCM) frameworks for causal inference. Adopting a neutral logical perspective, and drawing on previous…

Methodology · Statistics 2023-11-08 Duligur Ibeling , Thomas Icard

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm…

Machine Learning · Computer Science 2021-08-12 Weishen Pan , Sen Cui , Jiang Bian , Changshui Zhang , Fei Wang

Machine learning (ML) models can underperform on certain population groups due to choices made during model development and bias inherent in the data. We categorize sources of discrimination in the ML pipeline into two classes: aleatoric…

Machine Learning · Computer Science 2024-04-17 Hao Wang , Luxi He , Rui Gao , Flavio P. Calmon

Large language models have recently shown promising progress in mathematical reasoning when fine-tuned with human-generated sequences walking through a sequence of solution steps. However, the solution sequences are not formally structured…

Machine Learning · Computer Science 2022-12-07 Andrew J. Nam , Mengye Ren , Chelsea Finn , James L. McClelland

Causal models are notoriously difficult to validate because they make untestable assumptions regarding confounding. New scientific experiments offer the possibility of evaluating causal models using prediction performance. Prediction…

Machine Learning · Statistics 2021-10-27 James P. Long , Min Jin Ha

Causal representation learning in the anti-causal setting (labels cause features rather than the reverse) presents unique challenges requiring specialized approaches. We propose Anti-Causal Invariant Abstractions (ACIA), a novel…

Machine Learning · Computer Science 2025-10-22 Arman Behnam , Binghui Wang

Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They are studied in several communities, including synthetic corruption benchmarks for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Stefan Becker , Simon Weiss , Wolfgang Hübner , Michael Arens

Predictive models learned from historical data are widely used to help companies and organizations make decisions. However, they may digitally unfairly treat unwanted groups, raising concerns about fairness and discrimination. In this…

Machine Learning · Computer Science 2018-03-07 Yongkai Wu , Lu Zhang , Xintao Wu

We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases…

Computation and Language · Computer Science 2020-11-25 Michael A. Lepori

Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are non-causal: the training procedure is unaware of the causal…

Machine Learning · Computer Science 2019-11-05 Pim de Haan , Dinesh Jayaraman , Sergey Levine

An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one…

Artificial Intelligence · Computer Science 2023-05-09 Fabio Massimo Zennaro , Máté Drávucz , Geanina Apachitei , W. Dhammika Widanage , Theodoros Damoulas

Explanations are a fundamental element of how people make sense of the political world. Citizens routinely ask and answer questions about why events happen, who is responsible, and what could or should be done differently. Yet despite their…

Computation and Language · Computer Science 2025-12-04 Paulina Garcia-Corral