SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction

Sanghyeok Choi, Woosang Jeon, Kyuseok Yang, Taehyeong Kim


Abstract
Constructing Knowledge Graphs (KGs) from unstructured text provides a structured framework for knowledge representation and reasoning, yet current LLM-based approaches struggle with a fundamental trade-off: factual coverage often leads to relational fragmentation, while premature consolidation causes information loss. To address this, we propose SocraticKG, an automated KG construction method that introduces question-answer pairs as a structured intermediate representation to systematically unfold document-level semantics prior to triple extraction. By employing 5W1H-guided QA expansion, SocraticKG captures contextual dependencies and implicit relational links typically lost in direct KG extraction pipelines, providing explicit grounding in the source document that helps mitigate implicit reasoning errors. Evaluation on the MINE benchmark demonstrates that our approach effectively addresses the coverage-connectivity trade-off, achieving superior factual retention while maintaining high structural cohesion even as extracted knowledge volume substantially expands. These results highlight that QA-mediated semantic scaffolding plays a critical role in structuring semantics prior to KG extraction, enabling more coherent and reliable graph construction in subsequent stages.
Anthology ID:
2026.findings-acl.1951
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
39149–39169
Language:
URL:
https://aclanthology.org/2026.findings-acl.1951/
DOI:
10.18653/v1/2026.findings-acl.1951
Bibkey:
Cite (ACL):
Sanghyeok Choi, Woosang Jeon, Kyuseok Yang, and Taehyeong Kim. 2026. SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction. In Findings of the Association for Computational Linguistics: ACL 2026, pages 39149–39169, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction (Choi et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1951.pdf
Checklist:
 2026.findings-acl.1951.checklist.pdf