Social biases in LLMs are usually measured via bias benchmark datasets.
Current benchmarks have limitations in scope, grounding, quality, and human
effort required. Previous work has shown success with a community-sourced,
rather than crowd-sourced, approach to benchmark development. However, this
work still required considerable effort from annotators with relevant lived
experience. This paper explores whether an LLM (specifically, GPT-3.5-Turbo)
can assist with the task of developing a bias benchmark dataset from responses
to an open-ended community survey. We also extend the previous work to a new
community and set of biases: the Jewish community and antisemitism. Our
analysis shows that GPT-3.5-Turbo has poor performance on this annotation task
and produces unacceptable quality issues in its output. Thus, we conclude that
GPT-3.5-Turbo is not an appropriate substitute for human annotation in
sensitive tasks related to social biases, and that its use actually negates
many of the benefits of community-sourcing bias benchmarks.

通过对社区调查的回应，探讨 GPT-3.5-Turbo 是否能够促进社会偏见标准数据集的开发任务，研究发现 GPT-3.5-Turbo 在此注释任务中表现不佳，产生了无法接受的质量问题，因此推断 GPT-3.5-Turbo 不适合在涉及社会偏见的敏感任务中代替人工标注，并且使用它实际上废除了社区资源偏见标准的许多好处。