Dissecting Causal Biases
Accurately measuring discrimination in machine learning-based automated decision systems is required to address the vital issue of fairness between subpopulations and/or individuals. Any bias in measuring discrimination can lead to either amplification or underestimation of the true value of discrimination. This paper focuses on a class of bias originating in the way training data is generated and/or collected. We call such class causal biases and use tools from the field of causality to formally define and analyze such biases. Four sources of bias are considered, namely, confounding, selection, measurement, and interaction. The main contribution of this paper is to provide, for each source of bias, a closed-form expression in terms of the model parameters. This makes it possible to analyze the behavior of each source of bias, in particular, in which cases they are absent and in which other cases they are maximized. We hope that the provided characterizations help the community better understand the sources of bias in machine learning applications.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and …
Age/UnbiasedDecision MakingImage GenerationInterpretability Techniques for Deep Learning+1Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences
Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We …
Effects of Distributional Biases on Gradient-Based Causal Discovery in the Bivariate Categorical Case
Gradient-based causal discovery shows great potential for deducing causal structure from data in an efficient and scalable way. Those approaches however can be susceptible to distributional biases in the data they are tr…
Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to an…
Linguistic Acceptabilitynamed-entity-recognitionNamed Entity RecognitionQuantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from over-reliance on unimodal biases (e.g., lang…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)