Academic Journal
View in EDS

Large Language Model-Based Text-to-Cypher Generation for Question-Answering on Biomedical Knowledge Graphs.

Bibliographic Details
Title: Large Language Model-Based Text-to-Cypher Generation for Question-Answering on Biomedical Knowledge Graphs.
Authors: Seeha S; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital., Abdelmoula A; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital., Boeker M; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital., Modersohn L; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital., Pallaoro P; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.; Technical University of Munich, TUM School of Medicine and Health, Data Integration Center, TUM University Hospital.
Source: Studies in health technology and informatics [Stud Health Technol Inform] 2026 Sep 17; Vol. 340, pp. 179-186.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform Subsets: MEDLINE
Imprint Name(s): Original Publication: Amsterdam ; Washington, DC : IOS Press, 1991-
MeSH Terms: Information Storage and Retrieval*/methods , Large Language Models* , Natural Language Processing*, Humans
Abstract: Introduction: Knowledge graphs are widely adopted due to their flexible structure and ability to represent large-scale, heterogeneous data. However, as these graphs grow, the queries used to retrieve information become more complex, making efficient information retrieval and question answering more challenging.
Objective: This work investigates (1) the impact of few-shot versus zero-shot prompting on Cypher query generation, and (2) performance differences between small (∼7B) and mid-size (∼32B) large language models (LLMs) on both of these approaches.
Methods: We propose a system that translates natural language questions into Cypher queries for execution on a Neo4j knowledge graph and evaluates answer quality on the PrimeKG and BioHopR datasets. To address data protection and cost constraints, we focus on locally deployable LLMs that require no additional training, using zero-shot and few-shot prompting strategies.
Results: 32B models generate syntactically valid Cypher queries using only the knowledge graph schema information. Few-shot prompting with four examples improves F1 score by 35.7 percentage points (∼62% relative improvement) compared to zero-shot prompting. While 7B models struggle to generate syntactically valid queries in the zero-shot setting, few-shot prompting substantially improves their performance, enabling high query syntax validity and F1 scores above 80%.
Conclusion: Few-shot prompting heavily improves query generation quality and enables effective use of smaller models, supporting the practical deployment of locally hosted LLMs for knowledge graph question answering.
Contributed Indexing: Keywords: Database Management Systems; Factual Database; Information Storage and Retrieval; Large Language Models; Natural Language Processing
Entry Date(s): Date Created: 20260917 Date Completed: 20260917 Latest Revision: 20260917
Update Code: 20260918
DOI: 10.3233/SHTI261000
PMID: 42752482
Database: MEDLINE
FullText Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 42752482
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Large Language Model-Based Text-to-Cypher Generation for Question-Answering on Biomedical Knowledge Graphs.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Seeha+S%22">Seeha S</searchLink>; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.<br /><searchLink fieldCode="AU" term="%22Abdelmoula+A%22">Abdelmoula A</searchLink>; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.<br /><searchLink fieldCode="AU" term="%22Boeker+M%22">Boeker M</searchLink>; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.<br /><searchLink fieldCode="AU" term="%22Modersohn+L%22">Modersohn L</searchLink>; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.<br /><searchLink fieldCode="AU" term="%22Pallaoro+P%22">Pallaoro P</searchLink>; Technical University of Munich, TUM School of Medicine and Health, Institute for AI and Informatics in Medicine (AIIM), TUM University Hospital.; Technical University of Munich, TUM School of Medicine and Health, Data Integration Center, TUM University Hospital.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%229214582%22">Studies in health technology and informatics</searchLink> [Stud Health Technol Inform] 2026 Sep 17; Vol. 340, pp. 179-186.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22IOS+Press%22">IOS Press </searchLink><i>Country of Publication: </i>Netherlands <i>NLM ID: </i>9214582 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1879-8365 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2209269630%22">09269630 </searchLink><i>NLM ISO Abbreviation: </i>Stud Health Technol Inform <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Amsterdam ; Washington, DC : IOS Press, 1991-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval%22">Information Storage and Retrieval*</searchLink>/<searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Large+Language+Models%22">Large Language Models*</searchLink> <br /><searchLink fieldCode="MM" term="%22Natural+Language+Processing%22">Natural Language Processing*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Introduction: Knowledge graphs are widely adopted due to their flexible structure and ability to represent large-scale, heterogeneous data. However, as these graphs grow, the queries used to retrieve information become more complex, making efficient information retrieval and question answering more challenging.<br />Objective: This work investigates (1) the impact of few-shot versus zero-shot prompting on Cypher query generation, and (2) performance differences between small (∼7B) and mid-size (∼32B) large language models (LLMs) on both of these approaches.<br />Methods: We propose a system that translates natural language questions into Cypher queries for execution on a Neo4j knowledge graph and evaluates answer quality on the PrimeKG and BioHopR datasets. To address data protection and cost constraints, we focus on locally deployable LLMs that require no additional training, using zero-shot and few-shot prompting strategies.<br />Results: 32B models generate syntactically valid Cypher queries using only the knowledge graph schema information. Few-shot prompting with four examples improves F1 score by 35.7 percentage points (∼62% relative improvement) compared to zero-shot prompting. While 7B models struggle to generate syntactically valid queries in the zero-shot setting, few-shot prompting substantially improves their performance, enabling high query syntax validity and F1 scores above 80%.<br />Conclusion: Few-shot prompting heavily improves query generation quality and enables effective use of smaller models, supporting the practical deployment of locally hosted LLMs for knowledge graph question answering.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Database Management Systems; Factual Database; Information Storage and Retrieval; Large Language Models; Natural Language Processing
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260917 <i>Date Completed: </i>20260917 <i>Latest Revision: </i>20260917
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260918
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3233/SHTI261000
– Name: AN
  Label: PMID
  Group: ID
  Data: 42752482
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42752482
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3233/SHTI261000
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 179
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Information Storage and Retrieval methods
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
    Titles:
      – TitleFull: Large Language Model-Based Text-to-Cypher Generation for Question-Answering on Biomedical Knowledge Graphs.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Seeha S
      – PersonEntity:
          Name:
            NameFull: Abdelmoula A
      – PersonEntity:
          Name:
            NameFull: Boeker M
      – PersonEntity:
          Name:
            NameFull: Modersohn L
      – PersonEntity:
          Name:
            NameFull: Pallaoro P
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 17
              M: 09
              Text: 2026 Sep 17
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1879-8365
          Numbering:
            – Type: volume
              Value: 340
          Titles:
            – TitleFull: Studies in health technology and informatics
              Type: main
ResultId 1