Saved in:
Bibliographic Details
Main Authors: Roy, Amartya, Khanna, Danush, Mahapatra, Devanshu, Vasanthakumar, Das, Avirup, Ghosh, Kripabandhu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.16371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909325230866432
author Roy, Amartya
Khanna, Danush
Mahapatra, Devanshu
Vasanthakumar
Das, Avirup
Ghosh, Kripabandhu
author_facet Roy, Amartya
Khanna, Danush
Mahapatra, Devanshu
Vasanthakumar
Das, Avirup
Ghosh, Kripabandhu
contents This paper tackles the challenge of building robust and generalizable bias mitigation models for language. Recognizing the limitations of existing datasets, we introduce ANUBIS, a novel dataset with 1507 carefully curated sentence pairs encompassing nine social bias categories. We evaluate state-of-the-art models like T5, utilizing Supervised Fine-Tuning (SFT), Reinforcement Learning (PPO, DPO), and In-Context Learning (ICL) for effective bias mitigation. Our analysis focuses on multi-class social bias reduction, cross-dataset generalizability, and environmental impact of the trained models. ANUBIS and our findings offer valuable resources for building more equitable AI systems and contribute to the development of responsible and unbiased technologies with broad societal impact.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs
Roy, Amartya
Khanna, Danush
Mahapatra, Devanshu
Vasanthakumar
Das, Avirup
Ghosh, Kripabandhu
Computation and Language
This paper tackles the challenge of building robust and generalizable bias mitigation models for language. Recognizing the limitations of existing datasets, we introduce ANUBIS, a novel dataset with 1507 carefully curated sentence pairs encompassing nine social bias categories. We evaluate state-of-the-art models like T5, utilizing Supervised Fine-Tuning (SFT), Reinforcement Learning (PPO, DPO), and In-Context Learning (ICL) for effective bias mitigation. Our analysis focuses on multi-class social bias reduction, cross-dataset generalizability, and environmental impact of the trained models. ANUBIS and our findings offer valuable resources for building more equitable AI systems and contribute to the development of responsible and unbiased technologies with broad societal impact.
title Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs
topic Computation and Language
url https://arxiv.org/abs/2409.16371