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 2407.12812cs.CLcs.AI
收藏

构建面向政策与证据审查的可理解信息框架(BUMPER)——基于人工智能

Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI

Institute for Disease Modeling(疾病建模研究所);University of California, Davis(加州大学戴维斯分校)

Katherine A. Rosenfeld, Maike Sonnewald, Sonia J. Jindal, Kevin A. McCarthy, Joshua L. Proctor

AI总结:

本文提出BUMPER框架,利用大型语言模型将科学证据转化为政策行动,通过透明度、范围限制和不确定性度量增强可信度,并以麻疹控制政策为例展示其应用价值。

摘要:

我们介绍了一个利用大型语言模型(LLMs)构建面向政策与证据审查的可理解信息框架(BUMPER)。LLMs已被证明能够为理解和综合大型多样化媒体数据库提供接口。这为将科学证据转化为政策和行动提供了令人振奋的机遇,从而改善世界各地的生活水平。然而,这些模型也带来了与访问、可信度和问责相关的挑战。BUMPER框架建立在由同一批科学家(如个人贡献者、实验室、联盟)构建的科学知识库(如文档、代码、调查数据)之上。我们专注于通过透明度、范围限制、显式检查和不确定性度量来建立可信度的解决方案。LLMs正在被迅速采用,其后果尚未得到充分理解。该框架解决了关于LLMs可靠性及其在高风险应用中使用的开放性问题。我们提供了一个在卫生政策中的实际示例,涉及一个旨在为麻疹控制计划提供信息的模型。我们认为,该框架能够促进政策制定者对科学证据的可获取性和信心,推动研究者关注政策相关性和可转化性,并最终增加和加速用于政策决策的科学知识的影响。

英文摘要:

We introduce a framework for the use of large language models (LLMs) in Building Understandable Messaging for Policy and Evidence Review (BUMPER). LLMs are proving capable of providing interfaces for understanding and synthesizing large databases of diverse media. This presents an exciting opportunity to supercharge the translation of scientific evidence into policy and action, thereby improving livelihoods around the world. However, these models also pose challenges related to access, trust-worthiness, and accountability. The BUMPER framework is built atop a scientific knowledge base (e.g., documentation, code, survey data) by the same scientists (e.g., individual contributor, lab, consortium). We focus on a solution that builds trustworthiness through transparency, scope-limiting, explicit-checks, and uncertainty measures. LLMs are rapidly being adopted and consequences are poorly understood. The framework addresses open questions regarding the reliability of LLMs and their use in high-stakes applications. We provide a worked example in health policy for a model designed to inform measles control programs. We argue that this framework can facilitate accessibility of and confidence in scientific evidence for policymakers, drive a focus on policy-relevance and translatability for researchers, and ultimately increase and accelerate the impact of scientific knowledge used for policy decisions.

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。

↑