arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07371cs.CLcs.CY
收藏

BiasTestGPT:使用 ChatGPT 对语言模型进行社会偏见测试

BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models

California Institute of Technology(加州理工学院);NVIDIA(英伟达)

Rafal Kocielnik, Shrimai Prabhumoye, Vivian Zhang, Roy Jiang, R. Michael Alvarez, Anima Anandkumar

AI总结:

本文提出 BiasTestGPT,利用 ChatGPT 按任意社会群体与属性组合可控生成多样化测试句,并以开源框架接入 PLM,从而更有效地检测包括交叉性偏见在内的社会偏见。

摘要:

预训练语言模型(PLM)存在固有的社会偏见,这些偏见可能导致有害的现实世界影响。此类社会偏见通过 PLM 对一组测试句子中出现的不同社会群体和属性所输出的概率值来衡量。然而,偏见测试目前十分繁琐,因为测试句子要么来自有限的人工模板集合,要么需要昂贵的众包。相反,我们提出使用 ChatGPT,在用户任意指定测试句子中出现的社会群体与属性组合的情况下,可控地生成测试句子。与基于模板的方法相比,我们使用 ChatGPT 生成测试句子的方法在检测社会偏见方面更优,尤其是在交叉性偏见等具有挑战性的设置中。我们提出了一个开源的综合偏见测试框架(BiasTestGPT),托管在 HuggingFace 上,可接入任何开源 PLM 以进行偏见测试。对来自不同领域的专家进行的用户测试表明,他们有兴趣测试现代 AI 的社会偏见。我们的工具显著提高了他们对 PLM 中此类偏见的认识,被证明易于学习且用户友好。因此,我们通过为任意社会类别和属性组合自动大规模生成多样化测试句子,使领域专家能够对 PLM 进行无缝、开放式的社会偏见测试。

英文摘要:

Pretrained Language Models (PLMs) harbor inherent social biases that can result in harmful real-world implications. Such social biases are measured through the probability values that PLMs output for different social groups and attributes appearing in a set of test sentences. However, bias testing is currently cumbersome since the test sentences are generated either from a limited set of manual templates or need expensive crowd-sourcing. We instead propose using ChatGPT for the controllable generation of test sentences, given any arbitrary user-specified combination of social groups and attributes appearing in the test sentences. When compared to template-based methods, our approach using ChatGPT for test sentence generation is superior in detecting social bias, especially in challenging settings such as intersectional biases. We present an open-source comprehensive bias testing framework (BiasTestGPT), hosted on HuggingFace, that can be plugged into any open-source PLM for bias testing. User testing with domain experts from various fields has shown their interest in being able to test modern AI for social biases. Our tool has significantly improved their awareness of such biases in PLMs, proving to be learnable and user-friendly. We thus enable seamless open-ended social bias testing of PLMs by domain experts through an automatic large-scale generation of diverse test sentences for any combination of social categories and attributes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑