English

Fairness-aware Summarization for Justified Decision-Making

Artificial Intelligence 2022-02-11 v2 Computation and Language Computers and Society

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.

Keywords

Cite

@article{arxiv.2107.06243,
  title  = {Fairness-aware Summarization for Justified Decision-Making},
  author = {Moniba Keymanesh and Tanya Berger-Wolf and Micha Elsner and Srinivasan Parthasarathy},
  journal= {arXiv preprint arXiv:2107.06243},
  year   = {2022}
}

Comments

22 pages, 9 figures

R2 v1 2026-06-24T04:09:45.036Z