arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09720cs.CLcs.AI
收藏

考虑不确定性的动态知识图谱用于可靠的问答

Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering

Fujitsu Research(Fujitsu 研究所);Macquarie University(麦考瑞大学)

Yu Takahashi, Shun Takeuchi, Kexuan Xin, Guillaume Pelat, Yoshiaki Ikai, Junya Saito, Jonathan Vitale, Shlomo Berkovsky, Amin Beheshti

AI总结:

本文提出了一种考虑不确定性的动态知识图谱框架,通过动态构建、置信度评分和交互式界面提升问答系统的可靠性和透明度。

摘要:

问答系统正越来越多地在各个领域中部署。然而,当检索到的证据不完整、嘈杂或不确定时,其可靠性会受到质疑。现有的基于知识图谱(KG)的问答框架通常将事实表示为静态且确定性的,无法捕捉信息的演变性质和推理中的固有不确定性。我们展示了一个考虑不确定性的动态知识图谱框架,该框架结合了(i)动态构建的演变知识图谱、(ii)置信度评分和不确定性的检索,以及(iii)用于可靠和可解释的问答的交互式界面。我们的系统展示了如何通过使用户能够探索动态图谱、检查带有置信度注释的三元组,并比较基线与置信度意识答案,使问答更加稳健和透明。本演示的目标用户是临床数据科学家和临床医生,我们将在医疗领域实例化该框架:从电子健康记录中构建个性化知识图谱,可视化患者就诊中的不确定性,并评估其对死亡预测任务的影响。这个用例展示了考虑不确定性的动态知识图谱在提高高风险应用中问答可靠性方面的广阔前景。

英文摘要:

Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Existing knowledge graph (KG) based QA frameworks typically represent facts as static and deterministic, failing to capture the evolving nature of information and the uncertainty inherent in reasoning. We present a demonstration of uncertainty-aware dynamic KGs, a framework that combines (i) dynamic construction of evolving KGs, (ii) confidence scoring and uncertainty-aware retrieval, and (iii) an interactive interface for reliable and interpretable QA. Our system highlights how uncertainty modeling can make QA more robust and transparent by enabling users to explore dynamic graphs, inspect confidence-annotated triples, and compare baseline versus confidence-aware answers. The target users of this demo are clinical data scientists and clinicians, and we instantiate the framework in healthcare: constructing personalized KGs from electronic health records, visualizing uncertainty across patient visits, and evaluating its impact on a mortality prediction task. This use case demonstrates the broader promise of uncertainty-aware dynamic KGs for enhancing QA reliability in high-stakes applications.

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。

↑