Human-Guided Fair Classification for Natural Language Processing
OPEN ACCESS
Author / Producer
Date
2023
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
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.
Permanent link
Publication status
published
External links
Editor
Book title
The Eleventh International Conference on Learning Representations
Journal / series
Volume
Pages / Article No.
Publisher
OpenReview
Event
11th International Conference on Learning Representations (ICLR 2023)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Individual fairness; Style transfer; NLP; Crowdsourcing; Human Evaluation
Organisational unit
09627 - Ash, Elliott / Ash, Elliott
03948 - Vechev, Martin / Vechev, Martin
02219 - ETH AI Center / ETH AI Center
02150 - Dep. Informatik / Dep. of Computer Science