Saved in:
Bibliographic Details
Main Authors: de Swart, Milena, Hengst, Floris den, Chen, Jieying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.13548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915160859344896
author de Swart, Milena
Hengst, Floris den
Chen, Jieying
author_facet de Swart, Milena
Hengst, Floris den
Chen, Jieying
contents This paper addresses the critical need for detecting bias in government documents, an underexplored area with significant implications for governance. Existing methodologies often overlook the unique context and far-reaching impacts of governmental documents, potentially obscuring embedded biases that shape public policy and citizen-government interactions. To bridge this gap, we introduce the Dutch Government Data for Bias Detection (DGDB), a dataset sourced from the Dutch House of Representatives and annotated for bias by experts. We fine-tune several BERT-based models on this dataset and compare their performance with that of generative language models. Additionally, we conduct a comprehensive error analysis that includes explanations of the models' predictions. Our findings demonstrate that fine-tuned models achieve strong performance and significantly outperform generative language models, indicating the effectiveness of DGDB for bias detection. This work underscores the importance of labeled datasets for bias detection in various languages and contributes to more equitable governance practices.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detecting Linguistic Bias in Government Documents Using Large language Models
de Swart, Milena
Hengst, Floris den
Chen, Jieying
Computation and Language
This paper addresses the critical need for detecting bias in government documents, an underexplored area with significant implications for governance. Existing methodologies often overlook the unique context and far-reaching impacts of governmental documents, potentially obscuring embedded biases that shape public policy and citizen-government interactions. To bridge this gap, we introduce the Dutch Government Data for Bias Detection (DGDB), a dataset sourced from the Dutch House of Representatives and annotated for bias by experts. We fine-tune several BERT-based models on this dataset and compare their performance with that of generative language models. Additionally, we conduct a comprehensive error analysis that includes explanations of the models' predictions. Our findings demonstrate that fine-tuned models achieve strong performance and significantly outperform generative language models, indicating the effectiveness of DGDB for bias detection. This work underscores the importance of labeled datasets for bias detection in various languages and contributes to more equitable governance practices.
title Detecting Linguistic Bias in Government Documents Using Large language Models
topic Computation and Language
url https://arxiv.org/abs/2502.13548