Holistically measuring societal biases of large language models is crucial
for detecting and reducing ethical risks in highly capable AI models. In this
work, we present a Chinese Bias Benchmark dataset that consists of over 100K
questions jointly constructed by human experts and generative language models,
covering stereotypes and societal biases in 14 social dimensions related to
Chinese culture and values. The curation process contains 4 essential steps:
bias identification via extensive literature review, ambiguous context
generation, AI-assisted disambiguous context generation, snd manual review \&
recomposition. The testing instances in the dataset are automatically derived
from 3K+ high-quality templates manually authored with stringent quality
control. The dataset exhibits wide coverage and high diversity. Extensive
experiments demonstrate the effectiveness of the dataset in detecting model
bias, with all 10 publicly available Chinese large language models exhibiting
strong bias in certain categories. Additionally, we observe from our
experiments that fine-tuned models could, to a certain extent, heed
instructions and avoid generating outputs that are morally harmful in some
types, in the way of "moral self-correction". Our dataset and results are
publicly available at
\href{https://github.com/YFHuangxxxx/CBBQ}{this https URL},
offering debiasing research opportunities to a widened community.

本文提供一个超过 10 万个问题的中文偏见基准数据集，包括与中国文化和价值观相关的 14 个社会维度中的刻板印象和社会偏见，通过广泛文献综述、生成环境、AI 辅助去歧义生成、手动审核和重组等步骤，展示了数据集的广泛覆盖和高多样性，实验表明所有 10 个公开可用的中文大型语言模型在某些类别中存在强烈的偏见。