收藏切换
A Graph RAG Approach to Enhance Explainability in Dataset Discovery
收藏切换
PDF
Claudia Diamantini1, Alessandro Mele1, Alex Mircoli1, Domenico Potena1, Cristina Rossetti1, 2, Emanuele Storti1
Data Science and Engineering | 2026, 11(1) : 30 - 52
Less
收藏切换
Data Science and Engineering | 2026, 11(1): 30-52
RESEARCH PAPERS
A Graph RAG Approach to Enhance Explainability in Dataset Discovery
Full
Claudia Diamantini1, Alessandro Mele1, Alex Mircoli1, Domenico Potena1, Cristina Rossetti1, 2, Emanuele Storti1
Affiliations
Published: 2026-03-01 doi: 10.1007/s41019-025-00313-x
Outline
收藏切换

Discovering relevant datasets in large, heterogeneous data ecosystems, such as Data Lakes or Data spaces, is a complex task, often hindered by a lack of transparency and user-centric explanations in the discovery process. Explainability is critical for enabling users to understand why specific datasets are recommended, what information they contain, and how they align with user-defined criteria and preferences. To address these challenges, this work proposes a novel Graph Retrieval-Augmented Generation (Graph RAG) framework to enhance explainability in a platform for discovery of summary data sources. The proposed approach leverages a Knowledge Graph (KG) to interpret user requests, extracting relevant contextual information. These enriched requests are then transformed by a Large Language Model (LLM) into actionable dataset queries for a dataset discovery platform. Candidate solutions are evaluated and enriched with statistical insights on value distributions and contextual knowledge from the KG. Finally, the LLM ranks these solutions based on user preferences, producing a final report. This dual strategy of query enrichment and contextual explanation fosters transparency and enhances user understanding of the discovery process. We demonstrate the effectiveness of the approach through an experimental validation, highlighting its potential to improve both the accuracy and interpretability of dataset discovery.

Dataset discovery  /  Knowledge graph  /  Retrieval augmentation generation  /  LLM  /  Multidimensional model
Claudia Diamantini, Alessandro Mele, Alex Mircoli, Domenico Potena, Cristina Rossetti, Emanuele Storti. A Graph RAG Approach to Enhance Explainability in Dataset Discovery[J]. Data Science and Engineering, 2026 , 11 (1) : 30 -52 . DOI: 10.1007/s41019-025-00313-x
  • MUR — DM(118/2023)
  • project PNRR-NGEU
  • project Vitality — Project Code(ECS00000041; CUP I33C22001330007)
  • National Recovery and Resilience Plan (NRRP)
  • 'territorial leaders in R&D' — Innovation Ecosystems - Project 'Innovation, digitalization and sustainability(0001057.23-06-2022)
  • NextGenerationEU
Year 2026 volume 11 Issue 1
PDF
39
10
Cite this Article
BibTeX
Article Info
doi: 10.1007/s41019-025-00313-x
  • Receive Date:2025-02-16
  • Online Date:2026-08-06
  • Published:2026-03-01
Article Data
Affiliations
History
  • Received:2025-02-16
  • Revised:2025-07-10
  • Accepted:2025-08-12
Funding
MUR — DM(118/2023)
project PNRR-NGEU
project Vitality — Project Code(ECS00000041; CUP I33C22001330007)
National Recovery and Resilience Plan (NRRP)
'territorial leaders in R&D' — Innovation Ecosystems - Project 'Innovation, digitalization and sustainability(0001057.23-06-2022)
NextGenerationEU
Affiliations
    1Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche, via Brecce Bianche, Ancona 60131, Italy
    2Dipartimento di Automatica e Informatica, Politecnico di Torino, Corso Duca degli Abruzzi, 24, Torino 10129, Italy

Corresponding:

Emanuele Storti 
References
Share
https://castjournals.cast.org.cn/joweb/dse/EN/10.1007/s41019-025-00313-x
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT