Work

Disentangling Biased Representations: A Causal Intervention Framework for Fairer NLP Models

Year: 2025

Type: conference-paper

Abstract: Natural language processing (NLP) systems often inadvertently encode and amplify social biases through entangled representations of demographic attributes and task-related attributes.To mitigate this, we propose a novel framework that combines causal analysis with practical intervention strategies.The method leverages attribute-specific prompting to isolate sensitive attributes while applying information-theoretic constraints to minimize spurious correlations.Experiments across six language models and two classification tasks demonstrate its effectiveness.We hope this work will provide the NLP community with a causal disentanglement perspective for achieving fairness in NLP systems.

Source: Workshop on Gender Bias in Natural Language Processing (GeBNLP)

DOI: 10.18653/v1/2025.gebnlp-1.33

Authors: Yangge Qian, Yilong Hu, Siqi Zhang, Xu Gu, Xiaolin Qin

Institutions: Chinese Academy of Sciences, University of Chinese Academy of Sciences

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

SDG: Reduced inequalities

Open Access status: hybrid

OpenAlex ID: W4412944414