LLM-Driven Progressive Semantic Verification with Intermediate-State Transitions for Multi-Hop Knowledge Graph Question Answering
Information · 09.11.2026 · 17 (11) · 1119
DOI: 10.3390/info17111119 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 09.11.2026. Verfasst von Zicheng Zuo und 4 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Talent Development Fund.
Abstract (Originalsprache)
Complex multi-hop knowledge graph question answering requires models to maintain reliable intermediate states while reasoning over multiple relations. Existing methods primarily emphasize subgraph retrieval and candidate relevance scoring, while the semantic eligibility of model-generated intermediate entities is often left implicit during inference. Consequently, a structurally plausible candidate may be used to update the reasoning state even when it does not satisfy the current local objective. To address this issue, we propose ProVeST, a progressive semantic verification framework with gated state transitions. ProVeST converts a complex question into dependent sub-questions, applies question-conditioned structural scoring to screen candidate entities, and uses a large language model (LLM) to verify each retained entity together with its path context. Only verified entities can update the next-hop reasoning state. Experiments with three LLM backbones on WebQuestionsSP (WebQSP) and ComplexWebQuestions (CWQ) demonstrate the applicability of ProVeST.
Förderung
- Xinjiang Talent Development Fund
Zitieren
APA
Zuo, Z., Cheng, K., Han, D., Liao, Y., & Tohti, T. (2026). LLM-Driven Progressive Semantic Verification with Intermediate-State Transitions for Multi-Hop Knowledge Graph Question Answering. Information, 17(11), 1119. https://doi.org/10.3390/info17111119
Vancouver
Zuo Z, Cheng K, Han D, Liao Y, Tohti T. LLM-Driven Progressive Semantic Verification with Intermediate-State Transitions for Multi-Hop Knowledge Graph Question Answering. Information. 2026;17(11):1119. doi:10.3390/info17111119
BibTeX
@article{Zuo2026,
author = {Zuo, Zicheng and Cheng, Kai and Han, Dongfang and Liao, Yuanyuan and Tohti, Turdi},
title = {LLM-Driven Progressive Semantic Verification with Intermediate-State Transitions for Multi-Hop Knowledge Graph Question Answering},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1119},
doi = {10.3390/info17111119}
}
EUVIMED