CORTEXA
← Browse
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, Sarah Callaghan

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.

View free PDFSource page

Related papers

arxivcs.CLcs.AIcs.DLcs.IRcs.LG2026-07-10

Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI

Miguel Arana-Catania, Catherine Conisbee, Matthew Kidd

Identifying and assigning keywords at scale is a technical, practical, and ethical challenge for crowdsourced collections. This article reports the findings of the "Extracting Keywords from Crowdsourced Collections" project, which used the Their Finest Hour Online Archive, a crow…

View free PDFSource page
arxivcs.CLcs.AIcs.DLcs.IR2026-06-29Cited by 5

Exploring Motivations for Algorithm Mention in the Domain of Natural Language Processing: A Deep Learning Approach

Yuzhuo Wang, Yi Xiang, Chengzhi Zhang

With the rise of data-intensive science, algorithms have become central to scientific research. In academic papers, algorithms are mentioned for different purposes, such as describing, using, comparing, or improving methods for specific research tasks. Identifying these purposes…

View free PDFSource page
arxivcs.CLcs.AIcs.DLcs.IRcs.LG2026-07-10

Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works

Miguel Arana-Catania, Gillian Pink, Glenn Roe

Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and historical editions, yet it remains a largely manual, labour-intensive process. This paper explores the application of m…

View free PDFSource page
arxivcs.CLcs.DLcs.HCcs.IR2026-06-30

Building a Multimodal Dataset of Academic Paper for Keyword Extraction

Jingyu Zhang, Xinyi Yan, Yi Xiang, Yingyi Zhang, Chengzhi Zhang

Up to this point, keyword extraction task typically relies solely on textual data. Neglecting visual details and audio features from image and audio modalities leads to deficiencies in information richness and overlooks potential correlations, thereby constraining the model's abi…

View free PDFSource page
arxivcs.AIcs.CLcs.IR2026-06-25

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Changxin Lao, Fei Pan, Guozhuang Ma, Han Li, Huihuang Lin, Jijun Shi, et al.

Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypothese…

View free PDFSource page
arxivcs.IRcs.AIcs.SE2026-07-03

Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark

Nishan Pantha, Pranath Reddy Kumbam, Sajil Awale, Pushwitha Krishnappa, Muthukumaran Ramasubramanian, Nidhi Jha, et al.

Scientists increasingly rely on open-source tools to support their research workflows, yet discovering relevant software among over 600 million GitHub repositories remains challenging. Existing code search benchmarks focus on general software engineering tasks and fail to capture…

View free PDFSource page