paper-with-me

Papers

FineDeb: A Debiasing Framework for Language Models

2023-02-05 · Akash Saravanan, Dhruv Mullick, Habibur Rahman, Nidhi Hegde

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with contextual debiasing of embeddings learned by pretrained language models. The model is then fine-tuned on a language modeling objective. Our results show that FineDeb offers stronger debiasing in comparison to other methods which often result in models as biased as the original language model. Our framework is generalizable for demographics with multiple classes, and we demonstrate its effectiveness through extensive experiments and comparisons with state of the art techniques. We release our code and data on GitHub.

📄 PDF Abstract BibTeX arXiv:2302.02453

Code (1)

akashsara/debiasing-language-models 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning

2022-07-06 · NAACL (GeBNLP) 2022 7 · Przemyslaw Joniak, Akiko Aizawa

Language model debiasing has emerged as an important field of study in the NLP community. Numerous debiasing techniques were proposed, but bias ablation remains an unaddressed issue. We demonstrate a novel framework for …

Language ModelingLanguage Modelling

Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness

2024-06-06 · Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue 외

While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language modeling ability and the risk of relearning social biases from downstream task-specific data…

Language ModelingLanguage Modelling

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

2025-09-18 · Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu arxiv

Multimodal Large Language Models (MLLMs) have shown substantial capabilities in integrating visual and textual information, yet frequently rely on spurious correlations, undermining their robustness and generalization in…

Multimodal ReasoningSentiment AnalysisSarcasm Detection

Does Debiasing Inevitably Degrade the Model Performance

2022-11-14 · Yiran Liu, Xiao Liu, Haotian Chen, Yang Yu

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation …

model

What Changed? Investigating Debiasing Methods using Causal Mediation Analysis

2022-06-01 · NAACL (GeBNLP) 2022 7 · Sullam Jeoung, Jana Diesner

Previous work has examined how debiasing language models affect downstream tasks, specifically, how debiasing techniques influence task performance and whether debiased models also make impartial predictions in downstrea…