McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

TL;DR

This paper introduces McBE, a comprehensive multi-task benchmark for evaluating biases in Chinese language models across multiple categories and tasks, addressing cultural and content diversity gaps in bias assessment.

Contribution

The paper presents the first extensive Chinese bias evaluation benchmark with multi-task capabilities, covering diverse bias categories and enabling comprehensive bias measurement in LLMs.

Findings

All evaluated LLMs exhibited varying degrees of bias.

The benchmark reveals differences in bias across models and categories.

Provides insights into bias characteristics specific to Chinese language models.

Abstract

As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets focus on English and North American culture, and their bias categories are not fully applicable to other cultures. The datasets grounded in the Chinese language and culture are scarce. More importantly, these datasets usually only support single evaluation tasks and cannot evaluate the bias from multiple aspects in LLMs. To address these issues, we present a Multi-task Chinese Bias Evaluation Benchmark (McBE) that includes 4,077 bias evaluation instances, covering 12 single bias categories, 82 subcategories and introducing 5 evaluation tasks, providing extensive category coverage, content diversity, and measuring comprehensiveness. Additionally, we evaluate several popular LLMs from different series and with parameter sizes. In general, all these LLMs demonstrated varying degrees of bias. We conduct an in-depth analysis of results, offering novel insights into bias in LLMs.