Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.089159
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

EviGraphRAG: Constraint-Verified Retrieval-Augmented Question Answering over Event Knowledge Graphs

Yuteng Sun, Yang Su*, Xu An Wang
School of Cryptography Engineering, Engineering University of People’s Armed Police, Xi’an, China
* Corresponding Author: Yang Su. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.089159

Received 15 July 2026; Accepted 02 September 2026; Published online 18 September 2026

Abstract

Event knowledge graphs support event-centric question answering by linking events to temporal, location, participant, and source-record information, but semantic relevance alone does not guarantee that a selected event satisfies every represented condition. We propose EviGraphRAG, a ranker-agnostic reliability layer that separates candidate ranking from exact verification and explicit abstention; EviGraphRAG-Struct is the default configuration. On the controlled oracle-normalized 4800-question benchmark, it preserves the unverified ranker’s positive-task outputs while attaining 0.9792 abstention accuracy. A separate 600-question set from machine-assisted drafting with deterministic construction and semantic-consistency checks shows realistic extraction noise: parser-based Macro Score is 0.7317 vs. 0.8717 with oracle constraints, with location extraction the largest weakness. After quoted-title-aware actor and location parsing repairs, the fixed predicted-cluster evaluation reaches 0.8448 Macro Score without positive false rejection. These results support a scoped claim: exact conjunction over represented event constraints and linked source-record connectivity can improve selective reliability, while parser quality and candidate retrieval remain limiting factors.

Keywords

Event knowledge graph; retrieval-augmented question answering; claim-constraint verification; trustworthy artificial intelligence; provenance; false support

  • 27

    View

  • 5

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link