arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2511.16961cs.AI

比较贝叶斯网络推断中的语言、视觉和综合解释

Comparing verbal, visual and combined explanations for Bayesian Network inferences

Dept of Data Science and AI, Faculty of Information Technology Monash University, Australia(数据科学与人工智能系,信息科技学院,墨尔本大学,澳大利亚);Dept of Human-Centred Computing, Faculty of Information Technology Monash University, Australia(以人为本计算系,信息科技学院,墨尔本大学,澳大利亚);Faculty of Information Technology Monash University, Australia(信息科技学院,墨尔本大学,澳大利亚)

Erik P. Nyberg, Steven Mascaro, Ingrid Zukerman, Michael Wybrow, Duc-Minh Vo, Ann Nicholson

AI总结:

本研究设计了语言和视觉扩展以提升贝叶斯网络推断的可解释性,并通过实验发现综合使用语言和视觉模态能更有效地帮助用户理解推理过程。

摘要:

贝叶斯网络(BNs)是辅助概率推理的重要工具,但尽管被视为透明模型,人们仍然难以理解它们。此外,当前的用户界面(UIs)仍然没有明确解释BNs的推理过程。为了解决这个问题,我们设计了语言和视觉扩展,以标准BN UI为基础,引导用户了解常见的推理模式。我们进行了一项用户研究,比较了我们的语言、视觉和综合UI扩展,以及基线UI。我们的主要发现是:(1)对于有关观察的影响、使这种影响成为可能的路径以及观察如何影响其他观察的影响的问题,用户在三种扩展类型中都比基线UI表现更好;(2)在某些问题类型中,使用语言和视觉模态相结合比单独使用其中一种模态更好。

英文摘要:

Bayesian Networks (BNs) are an important tool for assisting probabilistic reasoning, but despite being considered transparent models, people have trouble understanding them. Further, current User Interfaces (UIs) still do not clarify the reasoning of BNs. To address this problem, we have designed verbal and visual extensions to the standard BN UI, which can guide users through common inference patterns. We conducted a user study to compare our verbal, visual and combined UI extensions, and a baseline UI. Our main findings are: (1) users did better with all three types of extensions than with the baseline UI for questions about the impact of an observation, the paths that enable this impact, and the way in which an observation influences the impact of other observations; and (2) using verbal and visual modalities together is better than using either modality alone for some of these question types.

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。

↑