Saved in:
Bibliographic Details
Main Authors: Li, Haoxuan, Ma, Mingyu Derek, Huang, Jen-tse, Weng, Zhaotian, Wang, Wei, Zhao, Jieyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04855
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912313117769728
author Li, Haoxuan
Ma, Mingyu Derek
Huang, Jen-tse
Weng, Zhaotian
Wang, Wei
Zhao, Jieyu
author_facet Li, Haoxuan
Ma, Mingyu Derek
Huang, Jen-tse
Weng, Zhaotian
Wang, Wei
Zhao, Jieyu
contents Detecting biases in structured data is a complex and time-consuming task. Existing automated techniques are limited in diversity of data types and heavily reliant on human case-by-case handling, resulting in a lack of generalizability. Currently, large language model (LLM)-based agents have made significant progress in data science, but their ability to detect data biases is still insufficiently explored. To address this gap, we introduce the first end-to-end, multi-agent synergy framework, BIASINSPECTOR, designed for automatic bias detection in structured data based on specific user requirements. It first develops a multi-stage plan to analyze user-specified bias detection tasks and then implements it with a diverse and well-suited set of tools. It delivers detailed results that include explanations and visualizations. To address the lack of a standardized framework for evaluating the capability of LLM agents to detect biases in data, we further propose a comprehensive benchmark that includes multiple evaluation metrics and a large set of test cases. Extensive experiments demonstrate that our framework achieves exceptional overall performance in structured data bias detection, setting a new milestone for fairer data applications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04855
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
Li, Haoxuan
Ma, Mingyu Derek
Huang, Jen-tse
Weng, Zhaotian
Wang, Wei
Zhao, Jieyu
Artificial Intelligence
Detecting biases in structured data is a complex and time-consuming task. Existing automated techniques are limited in diversity of data types and heavily reliant on human case-by-case handling, resulting in a lack of generalizability. Currently, large language model (LLM)-based agents have made significant progress in data science, but their ability to detect data biases is still insufficiently explored. To address this gap, we introduce the first end-to-end, multi-agent synergy framework, BIASINSPECTOR, designed for automatic bias detection in structured data based on specific user requirements. It first develops a multi-stage plan to analyze user-specified bias detection tasks and then implements it with a diverse and well-suited set of tools. It delivers detailed results that include explanations and visualizations. To address the lack of a standardized framework for evaluating the capability of LLM agents to detect biases in data, we further propose a comprehensive benchmark that includes multiple evaluation metrics and a large set of test cases. Extensive experiments demonstrate that our framework achieves exceptional overall performance in structured data bias detection, setting a new milestone for fairer data applications.
title BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2504.04855