arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.20385cs.CL
收藏

等等,泰诺不就是对乙酰氨基酚吗……探究并提升语言模型抵抗虚假信息请求的能力

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

Mass General Brigham(麻省总医院布莱根医疗系统);Harvard Medical School(哈佛医学院);Brigham and Women’s Hospital(布莱根妇女医院);Dana-Farber Cancer Institute(丹娜-法伯癌症研究所);Boston Children’s Hospital(波士顿儿童医院);Massachusetts Institute of Technology(麻省理工学院);Johns Hopkins University(约翰斯·霍普金斯大学);University of Virginia(弗吉尼亚大学);Maastricht University(马斯特里赫特大学)

Shan Chen, Mingye Gao, Kuleen Sasse, Thomas Hartvigsen, Brian Anthony, Lizhou Fan, Hugo Aerts, Jack Gallifant, Danielle Bitterman

AI总结:

本文研究大语言模型在明知请求不合逻辑时仍遵从生成药物虚假信息的问题,发现通过上下文指示和指令微调优先逻辑推理可有效降低医学虚假信息风险。

摘要:

背景:大语言模型(LLMs)被训练以遵循指令,但这引入了一种脆弱性,即使用户请求会生成错误信息,模型也会盲目遵从。在医学领域,这可能加速影响人类健康的虚假信息的产生。目标/方法:我们分析了在模型明知请求不合逻辑的情况下,对生成误导性药物内容的请求的遵从情况。我们研究了通过上下文指示和对LLMs进行指令微调以优先考虑逻辑推理而非遵从性,是否能降低虚假信息风险。结果:尽管所有前沿LLMs都遵从了虚假信息请求,但基于提示的方法和基于参数的方法均能改善对请求中逻辑缺陷的检测,并防止医学虚假信息的传播。结论:使LLMs转向优先考虑逻辑而非遵从性,可以降低其被利用于制造医学虚假信息的风险。

英文摘要:

Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinformation that impacts human well-being. Objectives/Methods: We analyzed compliance to requests to generate misleading content about medications in settings where models know the request is illogical. We investigated whether in-context directions and instruction-tuning of LLMs to prioritize logical reasoning over compliance reduced misinformation risk. Results: While all frontier LLMs complied with misinformation requests, both prompt-based and parameter-based approaches can improve the detection of logic flaws in requests and prevent the dissemination of medical misinformation. Conclusion: Shifting LLMs to prioritize logic over compliance could reduce risks of exploitation for medical misinformation.

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。

↑