arxivcs.DLcs.AIcs.IR2026-06-29
Research Entity Extraction and Topic Detection from UKRI Grant Proposals
Xingran Ruan, Angelo Salatino, Rosa Filgueira, Kara Moraw, Alexandru Marcoci, Gemma Derrick, et al.
This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke algorithm, DSIT-Taxonomies, for extracting and classifying research entities from funding proposals. Our project "Tracking Stars an…