Fairness-aware Summarization for Justified Decision-Making

TL;DR

This paper introduces a fairness-aware summarization method for natural language explanations in decision models, aiming to improve fairness in both outcomes and justifications, especially in sensitive domains.

Contribution

It proposes a novel multi-task neural approach that extracts fair, high-utility summaries from biased explanations to enhance decision fairness and robustness against data poisoning.

Findings

Reduces demographic leakage in explanations

Moderately improves fairness in decision outcomes

Effectively detects and counters data poisoning attacks

Abstract

In consequential domains such as recidivism prediction, facility inspection, and benefit assignment, it's important for individuals to know the decision-relevant information for the model's prediction. In addition, predictions should be fair both in terms of the outcome and the justification of the outcome. In other words, decision-relevant features should provide sufficient information for the predicted outcome and should be independent of the membership of individuals in protected groups such as race and gender. In this work, we focus on the problem of (un)fairness in the justification of the text-based neural models. We tie the explanatory power of the model to fairness in the outcome and propose a fairness-aware summarization mechanism to detect and counteract the bias in such models. Given a potentially biased natural language explanation for a decision, we use a multi-task neural model and an attribution mechanism based on integrated gradients to extract high-utility and low-bias justifications in form of a summary. The extracted summary is then used for training a model to make decisions for individuals. Results on several real world datasets suggest that our method drastically limits the demographic leakage in the input (fairness in justification) while moderately enhancing the fairness in the outcome. Our model is also effective in detecting and counteracting several types of data poisoning attacks that synthesize race-coded reasoning or irrelevant justifications.