Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering

TL;DR

This paper introduces a framework for dynamic, uncertainty-aware knowledge graphs that improve the reliability and interpretability of question answering systems, especially in sensitive domains like healthcare.

Contribution

It presents a novel system combining dynamic knowledge graph construction, confidence scoring, and interactive visualization to enhance QA robustness and transparency.

Findings

Improved answer reliability through uncertainty modeling

Enhanced interpretability with confidence-annotated triples

Demonstrated effectiveness in healthcare data and mortality prediction

Abstract

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.