Towards Efficient Knowledge Graph Generation From Textbooks: A Dual Framework Approach

Simple item page
dc.contributor.advisorBaraniuk, Richard Gen_US
dc.creatorHatchett, Johaunen_US
dc.date.accessioned2025-05-16T14:40:20Zen_US
dc.date.available2025-05-16T14:40:20Zen_US
dc.date.created2025-05en_US
dc.date.issued2025-02-05en_US
dc.date.submittedMay 2025en_US
dc.date.updated2025-05-16T14:40:21Zen_US
dc.description.abstractThe recent proliferation of LLMs necessitates a strategy for addressing these models' deleterious shortcomings: hallucination, and lack of explainability. Knowledge graphs (KGs) have gained attention as a potential solution to these problems, as they can serve as a traceable, factual database for LLMs; however, constructing high-quality KGs efficiently remains a challenge. To address these challenges, this thesis proposes Words2Wisdom, a logic-informed, LLM-based framework for generating quality KGs from textbooks. Words2Wisdom creates expressive KGs by leveraging the structure of propositional logic, and ensures accurate fact representation, demonstrating knowledge validity (precision) greater than 95% when using the GPT-4o model in a few-shot environment. Our results suggest targeted fine-tuning and model specialization can further enhance KG quality. Furthermore, this thesis examines whether LLMs are able to assess the quality of KGs. We introduce Libra, a framework establishing a novel KG evaluation protocol for validating KGs against textbook sources. Preliminary results show high observed agreement between Libra and human experts, suggesting that KG construction and evaluation and can indeed be effectively automated, paving the way for future research on the role of LLMs in hallucination mitigation.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.urihttps://hdl.handle.net/1911/118353en_US
dc.language.isoenen_US
dc.subjectknowledge graphsen_US
dc.subjectlarge language modelsen_US
dc.titleTowards Efficient Knowledge Graph Generation From Textbooks: A Dual Framework Approachen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentApplied Physicsen_US
thesis.degree.disciplineApplied Physics/Electrical Engen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
HATCHETT-DOCUMENT-2025.pdf
Size:
768.72 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.98 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations