Human-Guided Fair Classification for Natural Language Processing

TL;DR

This paper introduces methods to improve fairness in NLP classifiers by aligning them with human perceptions of sensitive attribute perturbations, using unsupervised style transfer, GPT-3, and crowdsourcing validation.

Contribution

It proposes novel techniques combining unsupervised style transfer, GPT-3, and human feedback to discover and validate human-aligned fairness specifications in NLP.

Findings

Generated sentence pairs align with human fairness perceptions.

Limited human feedback effectively trains fairness-aware models.

Proposed methods outperform hardcoded approaches in capturing human intuition.

Abstract

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes such as gender or ethnicity. However, there is a gap between human intuition about these perturbations and the formal similarity specifications capturing them. While existing research has started to address this gap, current methods are based on hardcoded word replacements, resulting in specifications with limited expressivity or ones that fail to fully align with human intuition (e.g., in cases of asymmetric counterfactuals). This work proposes novel methods for bridging this gap by discovering expressive and intuitive individual fairness specifications. We show how to leverage unsupervised style transfer and GPT-3's zero-shot capabilities to automatically generate expressive candidate pairs of semantically similar sentences that differ along sensitive attributes. We then validate the generated pairs via an extensive crowdsourcing study, which confirms that a lot of these pairs align with human intuition about fairness in the context of toxicity classification. Finally, we show how limited amounts of human feedback can be leveraged to learn a similarity specification that can be used to train downstream fairness-aware models.