Evaluating Debiasing Techniques for Intersectional Biases

2021-09-21 · EMNLP 2021 11 · Shivashankar Subramanian, Xudong Han, Timothy Baldwin, Trevor Cohn, Lea Frermann

Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or race, however many corpora involve multiple such attributes, possibly with higher cardinality. In this paper we argue that a truly fair model must consider `gerrymandering' groups which comprise not only single attributes, but also intersectional groups. We evaluate a form of bias-constrained model which is new to NLP, as well an extension of the iterative nullspace projection technique which can handle multiple protected attributes.

📄 PDF Abstract BibTeX arXiv:2109.10441

Code (0)

등록된 구현이 없습니다.

Debiasing Word Embeddings with Nonlinear Geometry

2022-08-29 · COLING 2022 10 · Lu Cheng, Nayoung Kim, Huan Liu

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that possibly correlate or intersect with each …

Word Embeddings

Measuring South Asian Biases in Large Language Models

2025-05-24 · Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee, Ziwei Zhu

Evaluations of Large Language Models (LLMs) often overlook intersectional and culturally specific biases, particularly in underrepresented multilingual regions like South Asia. This work addresses these gaps by conductin…

Benchmarking Intersectional Biases in NLP

2022-07-01 · NAACL 2022 7 · John Lalor, Yi Yang, Kendall Smith, Nicole Forsgren 외

There has been a recent wave of work assessing the fairness of machine learning models in general, and more specifically, on natural language processing (NLP) models built using machine learning techniques. While much wo…

Benchmarking BIG-bench Machine Learning Fairness

Assessing the quality and coherence of word embeddings after SCM-based intersectional bias mitigation

2026-01-07 · Eren Kocadag, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag arxiv

Static word embeddings often absorb social biases from the text they learn from, and those biases can quietly shape downstream systems. Prior work that uses the Stereotype Content Model (SCM) has focused mostly on single…

ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs

2024-02-19 · Pengrui Han, Rafal Kocielnik, Adhithya Saravanan, Roy Jiang 외

Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. Thi…

Data Augmentation Fairness