arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.00892cs.CLcs.AI
收藏

不被冒犯:从语言模型中诱导冒犯性内容

No Offense Taken: Eliciting Offensiveness from Language Models

New York University(纽约大学)

Anugya Srivastava, Rahul Ahuja, Rohith Mukku

AI总结:

本文针对语言模型安全测试,基于红队方法构建自动化测试用例生成流水线,利用小型公开LM评估不同目标模型与分类器,并生成可暴露冒犯性回复及失效模式的语料库。

摘要:

本工作于2022年5月完成。为了在真实世界中安全可靠地部署语言模型,测试必须具备鲁棒性。这种鲁棒性可以通过我们评估这些模型所用测试用例的难度和多样性来刻画。人在回路的测试用例生成存在局限,促使自动化测试用例生成方法兴起。具体而言,我们聚焦于Perez等人(2022)提出的“用语言模型对语言模型进行红队测试”。我们的贡献包括:开发一条通过红队测试实现自动化测试用例生成的流水线,该流水线利用公开可用的较小语言模型(LM);对不同目标LM和红队分类器进行实验;以及生成一个测试用例语料库,该语料库有助于从广泛部署的LM中诱导出冒犯性回复,并识别其失效模式。

英文摘要:

This work was completed in May 2022. For safe and reliable deployment of language models in the real world, testing needs to be robust. This robustness can be characterized by the difficulty and diversity of the test cases we evaluate these models on. Limitations in human-in-the-loop test case generation has prompted an advent of automated test case generation approaches. In particular, we focus on Red Teaming Language Models with Language Models by Perez et al.(2022). Our contributions include developing a pipeline for automated test case generation via red teaming that leverages publicly available smaller language models (LMs), experimenting with different target LMs and red classifiers, and generating a corpus of test cases that can help in eliciting offensive responses from widely deployed LMs and identifying their failure modes.

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。

↑