# Research Entity Extraction and Topic Detection from UKRI Grant Proposals

arXiv: https://arxiv.org/abs/2606.30304 · HTML: https://mlsanity.com/paper/2606.30304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [The CSO Classifier: Ontology-Driven Detection of Research Topics in Scholarly Articles](https://mlsanity.com/paper/2104.00948/) (2021)
- [Reference Coverage Analysis of OpenAlex compared to Web of Science and Scopus](https://mlsanity.com/paper/2401.16359/) (2024)
- [A Survey on Knowledge Organization Systems of Research Fields: Resources and Challenges](https://mlsanity.com/paper/2409.04432/) (2024)
- [SciNoBo : A Hierarchical Multi-Label Classifier of Scientific Publications](https://mlsanity.com/paper/2204.00880/) (2022)
- [Leveraging Large Language Models for Generating Research Topic Ontologies: A Multi-Disciplinary Study](https://mlsanity.com/paper/2508.20693/) (2025)

## Abstract (arXiv)

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 and Unicorns" aims to identify early signals of emerging research areas to inform public investment. Our methodology employed a three-stage pipeline, leveraging Mistral for primary entity extraction and mapping against the OpenAlex Topics taxonomy. We evaluated our approach across 42 proposals' abstracts from different areas and observed that Mistral and GPT-4o produce comparable, high-quality entity sets with significant semantic overlap, outperforming the fragmented DSIT-Taxonomies approach. Crucially, the Mistral-based approach achieved superior topic classification accuracy (90.5%) compared to the full DSIT-Taxonomies pipeline (71.4%). We conclude that Mistral offers a high-performance, operationally efficient, and secure solution for large-scale analysis of sensitive grant data.