arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.02161cs.HCcs.AI
收藏

Selenite:借助从大语言模型中引出的综合概览搭建在线意义建构支架

Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models

Google Research(谷歌研究院);Carnegie Mellon University(卡内基梅隆大学)

Michael Xieyang Liu, Tongshuang Wu, Tianying Chen, Franklin Mingzhe Li, Aniket Kittur, Brad A. Myers

AI总结:

针对在线意义建构工具的冷启动问题,本研究提出Selenite系统,利用大语言模型自动生成信息空间综合概览以启动用户意义建构,还可随使用适配,经实验验证能提升信息处理效率与用户体验。

摘要:

在陌生领域开展意义建构颇具挑战,需要用户投入大量精力,对照各类标准比较不同选项。此前研究及我们的先导性研究发现,用户若能预先阅读信息空间的概览(包含他人此前认为有用的标准)将从中获益。但现有意义建构工具存在“冷启动”问题——既需要过往用户大量输入才能生成并分享这类概览,且生成的概览还可能存在偏差、内容不完整。本研究中,我们推出全新系统Selenite,该系统将大语言模型(LLMs)用作推理机与知识检索器,自动生成选项与标准的综合概览,为用户的意义建构过程提供启动支持。后续Selenite还会随用户使用不断适配,帮助用户以系统且个性化的方式查找、阅读和浏览陌生信息。通过三项研究我们发现,Selenite能稳定生成准确、高质量的概览,显著加快用户的信息处理速度,并有效提升用户的整体理解水平与意义建构体验。

英文摘要:

Sensemaking in unfamiliar domains can be challenging, demanding considerable user effort to compare different options with respect to various criteria. Prior research and our formative study found that people would benefit from reading an overview of an information space upfront, including the criteria others previously found useful. However, existing sensemaking tools struggle with the "cold-start" problem -- it not only requires significant input from previous users to generate and share these overviews, but such overviews may also turn out to be biased and incomplete. In this work, we introduce a novel system, Selenite, which leverages Large Language Models (LLMs) as reasoning machines and knowledge retrievers to automatically produce a comprehensive overview of options and criteria to jumpstart users' sensemaking processes. Subsequently, Selenite also adapts as people use it, helping users find, read, and navigate unfamiliar information in a systematic yet personalized manner. Through three studies, we found that Selenite produced accurate and high-quality overviews reliably, significantly accelerated users' information processing, and effectively improved their overall comprehension and sensemaking experience.

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。

↑