Print Email Facebook Twitter Use of LLMs to Improve Affiliation Disambiguation in Alexandria3k Title Use of LLMs to Improve Affiliation Disambiguation in Alexandria3k Author Gupta, Dibyendu (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Spinellis, D. (mentor) Gousios, Giorgos (mentor) Langendoen, K.G. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2024-02-01 Abstract The growth of academic publications, heterogeneity of datasets and the absence of a globally accepted organization identifier introduce the challenge of affiliation disambiguation in bibliographic databases. In this paper, we create a baseline using the currently implemented algorithm for author affiliation linkage in Alexandria3k by comparing it to the ground truth. We aim to explore the usage of LLMs (GPT-4) in the Alexandria3k environment to disambiguate author affiliations. The proposed approach extracts the research organization from textual affiliations provided by researchers through their published works and cross-references the organization across the Research Organization Registry. Our process shows promising results and a significant improvement on the existing algorithm in terms of matching rate and identification of multiple affiliations. We discuss the margin of error in LLM results, limitations of the ground truth, and suggest future research directions. Subject Affiliation DisambiguationLLMAlexandria3kGround TruthGPT-4 To reference this document use: http://resolver.tudelft.nl/uuid:dde430e8-d0e0-4d63-9785-ed442e3574bd Part of collection Student theses Document type bachelor thesis Rights © 2024 Dibyendu Gupta Files PDF Use_of_LLMs_to_Improve_Af ... dria3k.pdf 401.61 KB Close viewer /islandora/object/uuid:dde430e8-d0e0-4d63-9785-ed442e3574bd/datastream/OBJ/view