SPARQL Query Generation Using LLMs for Medical Information Retrieval

Charalampos Doulaverakis; Giannis Vassiliou; Sotiris Batsakis; Nikos Papadakis; Georgia Eirini Trouli; Grigoris Antoniou

doi:10.1007/978-3-031-99554-5_8

SPARQL Query Generation Using LLMs for Medical Information Retrieval

Charalampos Doulaverakis, Giannis Vassiliou, Sotiris Batsakis, Nikos Papadakis, Georgia Eirini Trouli, Grigoris Antoniou

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Large Language Models (LLMs) have been the focus of Artificial Intelligence (AI) research recently but evaluation of their performance demonstrated their limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non existent facts, which is a major problem especially in critical tasks such as medical applications. In this work we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages Large Language Models (LLM) in order to allow for automatic SPARQL query generation from natural language by providing example entries of the dataset to the LLM so that it can analyze its structure. Preliminary results demonstrate the potential of our approach, and we provide an online demo so that users can experiment.

Original language	English
Title of host publication	The Semantic Web: ESWC 2025 Satellite Events
Subtitle of host publication	Portoroz, Slovenia, June 1–5, 2025, Proceedings
Editors	Edward Curry, Valentina Presutti, John McCrae, Mehwish Alam, Pieter Colpaert, Josiane Xavier Parreira, Diego Collarana, Marta Sabou, Andreas Harth, Pasquale Lisena
Publisher	Springer, Cham
Pages	40-44
Number of pages	5
Edition	1st
ISBN (Electronic)	9783031995545
ISBN (Print)	9783031995538
DOIs	https://doi.org/10.1007/978-3-031-99554-5_8
Publication status	Published - 13 Oct 2025
Event	22nd European Semantic Web Conference - Portoroz, Slovenia Duration: 1 Jun 2025 → 5 Jun 2025 https://2025.eswc-conferences.org/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	15832 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	22nd European Semantic Web Conference
Abbreviated title	ESWC 2025
Country/Territory	Slovenia
City	Portoroz
Period	1/06/25 → 5/06/25
Internet address	https://2025.eswc-conferences.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-031-99554-5_8Licence: Unspecified

Cite this

Doulaverakis, C., Vassiliou, G., Batsakis, S., Papadakis, N., Trouli, G. E., & Antoniou, G. (2025). SPARQL Query Generation Using LLMs for Medical Information Retrieval. In E. Curry, V. Presutti, J. McCrae, M. Alam, P. Colpaert, J. Xavier Parreira, D. Collarana, M. Sabou, A. Harth, & P. Lisena (Eds.), The Semantic Web: ESWC 2025 Satellite Events: Portoroz, Slovenia, June 1–5, 2025, Proceedings (1st ed., pp. 40-44). (Lecture Notes in Computer Science; Vol. 15832 LNCS). Springer, Cham. https://doi.org/10.1007/978-3-031-99554-5_8

Doulaverakis, Charalampos ; Vassiliou, Giannis ; Batsakis, Sotiris et al. / SPARQL Query Generation Using LLMs for Medical Information Retrieval. The Semantic Web: ESWC 2025 Satellite Events: Portoroz, Slovenia, June 1–5, 2025, Proceedings. editor / Edward Curry ; Valentina Presutti ; John McCrae ; Mehwish Alam ; Pieter Colpaert ; Josiane Xavier Parreira ; Diego Collarana ; Marta Sabou ; Andreas Harth ; Pasquale Lisena. 1st. ed. Springer, Cham, 2025. pp. 40-44 (Lecture Notes in Computer Science).

@inproceedings{ddd0ee544a184858b0e06c8e3bf4f0ea,

title = "SPARQL Query Generation Using LLMs for Medical Information Retrieval",

abstract = "Large Language Models (LLMs) have been the focus of Artificial Intelligence (AI) research recently but evaluation of their performance demonstrated their limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non existent facts, which is a major problem especially in critical tasks such as medical applications. In this work we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages Large Language Models (LLM) in order to allow for automatic SPARQL query generation from natural language by providing example entries of the dataset to the LLM so that it can analyze its structure. Preliminary results demonstrate the potential of our approach, and we provide an online demo so that users can experiment.",

keywords = "Knowledge graphs, LLM, Medical information retrieval, Natural language querying, SPARQL",

author = "Charalampos Doulaverakis and Giannis Vassiliou and Sotiris Batsakis and Nikos Papadakis and Trouli, \{Georgia Eirini\} and Grigoris Antoniou",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 22nd European Semantic Web Conference, ESWC 2025 ; Conference date: 01-06-2025 Through 05-06-2025",

year = "2025",

month = oct,

day = "13",

doi = "10.1007/978-3-031-99554-5\_8",

language = "English",

isbn = "9783031995538",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "40--44",

editor = "Edward Curry and Valentina Presutti and John McCrae and Mehwish Alam and Pieter Colpaert and \{Xavier Parreira\}, Josiane and Diego Collarana and Marta Sabou and Andreas Harth and Pasquale Lisena",

booktitle = "The Semantic Web: ESWC 2025 Satellite Events",

address = "Switzerland",

edition = "1st",

url = "https://2025.eswc-conferences.org/",

}

Doulaverakis, C, Vassiliou, G, Batsakis, S, Papadakis, N, Trouli, GE & Antoniou, G 2025, SPARQL Query Generation Using LLMs for Medical Information Retrieval. in E Curry, V Presutti, J McCrae, M Alam, P Colpaert, J Xavier Parreira, D Collarana, M Sabou, A Harth & P Lisena (eds), The Semantic Web: ESWC 2025 Satellite Events: Portoroz, Slovenia, June 1–5, 2025, Proceedings. 1st edn, Lecture Notes in Computer Science, vol. 15832 LNCS, Springer, Cham, pp. 40-44, 22nd European Semantic Web Conference, Portoroz, Slovenia, 1/06/25. https://doi.org/10.1007/978-3-031-99554-5_8

SPARQL Query Generation Using LLMs for Medical Information Retrieval. / Doulaverakis, Charalampos; Vassiliou, Giannis; Batsakis, Sotiris et al.
The Semantic Web: ESWC 2025 Satellite Events: Portoroz, Slovenia, June 1–5, 2025, Proceedings. ed. / Edward Curry; Valentina Presutti; John McCrae; Mehwish Alam; Pieter Colpaert; Josiane Xavier Parreira; Diego Collarana; Marta Sabou; Andreas Harth; Pasquale Lisena. 1st. ed. Springer, Cham, 2025. p. 40-44 (Lecture Notes in Computer Science; Vol. 15832 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SPARQL Query Generation Using LLMs for Medical Information Retrieval

AU - Doulaverakis, Charalampos

AU - Vassiliou, Giannis

AU - Batsakis, Sotiris

AU - Papadakis, Nikos

AU - Trouli, Georgia Eirini

AU - Antoniou, Grigoris

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2025/10/13

Y1 - 2025/10/13

N2 - Large Language Models (LLMs) have been the focus of Artificial Intelligence (AI) research recently but evaluation of their performance demonstrated their limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non existent facts, which is a major problem especially in critical tasks such as medical applications. In this work we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages Large Language Models (LLM) in order to allow for automatic SPARQL query generation from natural language by providing example entries of the dataset to the LLM so that it can analyze its structure. Preliminary results demonstrate the potential of our approach, and we provide an online demo so that users can experiment.

AB - Large Language Models (LLMs) have been the focus of Artificial Intelligence (AI) research recently but evaluation of their performance demonstrated their limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non existent facts, which is a major problem especially in critical tasks such as medical applications. In this work we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages Large Language Models (LLM) in order to allow for automatic SPARQL query generation from natural language by providing example entries of the dataset to the LLM so that it can analyze its structure. Preliminary results demonstrate the potential of our approach, and we provide an online demo so that users can experiment.

KW - Knowledge graphs

KW - LLM

KW - Medical information retrieval

KW - Natural language querying

KW - SPARQL

UR - https://www.scopus.com/pages/publications/105020236933

U2 - 10.1007/978-3-031-99554-5_8

DO - 10.1007/978-3-031-99554-5_8

M3 - Conference contribution

AN - SCOPUS:105020236933

SN - 9783031995538

T3 - Lecture Notes in Computer Science

SP - 40

EP - 44

BT - The Semantic Web: ESWC 2025 Satellite Events

A2 - Curry, Edward

A2 - Presutti, Valentina

A2 - McCrae, John

A2 - Alam, Mehwish

A2 - Colpaert, Pieter

A2 - Xavier Parreira, Josiane

A2 - Collarana, Diego

A2 - Sabou, Marta

A2 - Harth, Andreas

A2 - Lisena, Pasquale

PB - Springer, Cham

T2 - 22nd European Semantic Web Conference

Y2 - 1 June 2025 through 5 June 2025

ER -

Doulaverakis C, Vassiliou G, Batsakis S, Papadakis N, Trouli GE, Antoniou G. SPARQL Query Generation Using LLMs for Medical Information Retrieval. In Curry E, Presutti V, McCrae J, Alam M, Colpaert P, Xavier Parreira J, Collarana D, Sabou M, Harth A, Lisena P, editors, The Semantic Web: ESWC 2025 Satellite Events: Portoroz, Slovenia, June 1–5, 2025, Proceedings. 1st ed. Springer, Cham. 2025. p. 40-44. (Lecture Notes in Computer Science). Epub 2025 Oct 12. doi: 10.1007/978-3-031-99554-5_8