arXiv AI June 30, 2026 By Xingran Ruan, Angelo Salatino, Rosa Filgueira, Kara Moraw, Alexandru Marcoci, Gemma Derrick, Sarah Callaghan

Research Entity Extraction and Topic Detection from UKRI Grant Proposals

Read the original on arXiv AI →

arXiv:2606. 30304v1 Announce Type: cross Abstract: 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

llms

arXiv AI

Aug 10

SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension

arXiv:2608. 07254v1 Announce Type: cross Abstract: The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disciplines and research topics but often fail to capture the fine-grained conceptual structure of contemporary science.

By Daniele Raimondi, Feichi Lu, Oliver Grun, Mariia Eremina, Andrea Perlato

llms rag

arXiv AI

Jun 11

Mapping Scientific Literature with Large Language Models and Topic Modeling

arXiv:2510. 16152v2 Announce Type: replace-cross Abstract: Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science.

By Mason Smetana, Lev Khazanovich

llms nlp

arXiv AI

Jun 9

MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets

arXiv:2606. 07611v1 Announce Type: cross Abstract: This paper proposes an improved approach to the analysis of Mining Software Repositories (MSR) datasets via metadata enrichment, FAIRness assessment, and topic-driven analysis.

By Aabia Ather, Muhammad Usayd Ather, Qurat-Ul-Ain Somroo, Muhammad Khuram Shahzad

safety

arXiv AI

Jun 18

Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks

arXiv:2602. 19591v3 Announce Type: replace-cross Abstract: Small and Medium Enterprises (SMEs) constitute 99.

By Yijiashun Qi, Hanzhe Guo, Yijiazhen Qi

llms

arXiv Machine Learning

Jul 31

Baikal: Structured Search for Deep Research over Data Lakes

arXiv:2607. 27726v1 Announce Type: cross Abstract: Deep research over data lakes requires an LLM agent to investigate evidence across thousands of heterogeneous tables and passages to synthesize a report.

By Dhruv Agarwal, Rishitha Guttapalle Mohan, Aarti Kumari, Ashi Sinha, Athulya Anil, Kavitha Srinivas, Horst Samulowitz, Andrew McCallum

llms agents

arXiv AI

Jul 7

The Rise of Large Language Models and the Direction and Impact of US Federal Research Funding

arXiv:2601. 15485v3 Announce Type: replace-cross Abstract: Federal research funding shapes the direction, diversity, and impact of the US scientific enterprise.

By Yifan Qian, Zhe Wen, Alexander C. Furnas, Yue Bai, Erzhuo Shao, Dashun Wang

llms

Related stories

SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension

Mapping Scientific Literature with Large Language Models and Topic Modeling

MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets

Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks

Baikal: Structured Search for Deep Research over Data Lakes

The Rise of Large Language Models and the Direction and Impact of US Federal Research Funding