InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions

Bodhisattwa Prasad Majumder, Zexue He, Julian McAuley

Submission Type: Regular Short Paper

Submission Track: Interpretability, Interactivity, and Analysis of Models for NLP

Submission Track 2: Human-Centered NLP

Keywords: Debiasing, Language Models, Rationale, Interactions, User Interventions

Abstract:

Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race).
We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with explanations, rather than blindly eliminating it. This fair balance is often subjective and can be challenging to achieve algorithmically. We explore two interactive setups with a frozen predictive model and show that users able to provide feedback can achieve a better and \emph{fairer} balance between task performance and bias mitigation. In one setup, users, by interacting with test examples, further decreased bias in the explanations (5-8%) while maintaining the same prediction accuracy. In the other setup, human feedback was able to disentangle associated bias and predictive information from the input leading to superior bias mitigation and improved task performance (4-5%) simultaneously.

Submission Number: 5507