Document Open Access Logo

Are Diagnostic Concepts Within the Reach of LLMs?

Authors Anna Sztyber-Betley , Elodie Chanthery , Louise Travé-Massuyès , Silke Merkelbach , Karol Kukla, Maxence Glotin, Alexander Diedrich , Oliver Niggemann

PDF

File

Thumbnail PDF
PDF
OASIcs.DX.2025.2.pdf
  • Filesize: 1.15 MB
  • 20 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Computing methodologies → Knowledge representation and reasoning
Keywords
  • Fault Diagnosis
  • Large Language Models
  • LLMs
  • Model Based Diagnosis
  • MSO
  • Redundancy Relations
  • Conflicts
  • Diagnoses

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

Model-based diagnosis is a cornerstone of system health monitoring, allowing for the identification of faulty components based on observed behavior and a formal system model. However, obtaining a useful and reliable model is often an expensive and manual task. While the generation of a formal model was the aim of previous work, in this paper, we propose a methodology to use large language models to generate Minimal Structurally Overdetermined sets (MSOs). MSOs are specific subsets of the model equations from which diagnosis tests can be obtained. We investigate two different directions: (i) the large-language-models' ability to generate MSO sets for hybrid systems, similar to those generated by the well-known Fault Diagnosis Toolbox (FDT) (ii) the automated generation of MSOs for Boolean circuits, as well as the computation of the diagnoses. We thus show how both dynamic and static systems can be analysed by large-language models and how their output can be used for effective fault diagnosis. We evaluate our approach on a set of arithmetic and logic circuits, using OpenAI’s LLMs 4o-mini, o1, and o3-mini.

Cite As Get BibTex

Anna Sztyber-Betley, Elodie Chanthery, Louise Travé-Massuyès, Silke Merkelbach, Karol Kukla, Maxence Glotin, Alexander Diedrich, and Oliver Niggemann. Are Diagnostic Concepts Within the Reach of LLMs?. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 2:1-2:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/OASIcs.DX.2025.2

Author Details

Anna Sztyber-Betley
  • Warsaw University of Technology, Poland
Elodie Chanthery
  • LAAS-CNRS, INSA, University of Toulouse, France
Louise Travé-Massuyès
  • LAAS-CNRS, University of Toulouse, France
Silke Merkelbach
  • Fraunhofer IEM, Paderborn, Germany
Karol Kukla
  • Warsaw, Poland
Maxence Glotin
  • LAAS-CNRS, INSA, University of Toulouse, France
Alexander Diedrich
  • Helmut-Schmidt-University, Hamburg, Germany
Oliver Niggemann
  • Helmut-Schmidt-University, Hamburg, Germany

Funding

  • Chanthery, Elodie: The work is supported by ANITI through the French "Investing for the Future – P3IA" program under the Grant agreement n^oANR-19-P3IA-0004.
  • Travé-Massuyès, Louise: The work is supported by ANITI through the French "Investing for the Future – P3IA" program under the Grant agreement n^oANR-19-P3IA-0004.

Acknowledgements

This work has benefited from participation in Dagstuhl Seminar 24031 "Fusing Causality, Reasoning, and Learning for Fault Management and Diagnosis".

Supplementary Materials

References

  1. J-Ph Cassar and M Staroswiecki. A structural approach for the design of failure detection and identification systems. IFAC Proceedings Volumes, 30(6):841-846, 1997. Google Scholar
  2. Marie-Odile Cordier, Philippe Dague, Michel Dumas, François Lévy, Jacky Montmain, Marcel Staroswiecki, and Louise Travé-Massuyes. A comparative analysis of ai and control theory approaches to model-based diagnosis. In ECAI, pages 136-140, 2000. Google Scholar
  3. Akshay J Dave, Tat Nghia Nguyen, and Richard B Vilim. Integrating llms for explainable fault diagnosis in complex systems. arXiv preprint arXiv:2402.06695, 2024. URL: https://doi.org/10.48550/arXiv.2402.06695.
  4. Teresa Escobet, Anibal Bregon, Belarmino Pulido, and Vicenç Puig. Fault Diagnosis of Dynamic Systems. Springer, 2019. Google Scholar
  5. Erik Frisk, Mattias Krysander, and Daniel Jung. A toolbox for analysis and design of model based diagnosis systems for large scale models. IFAC-PapersOnLine, 50(1):3287-3293, 2017. Google Scholar
  6. Sungmin Kang, Gabin An, and Shin Yoo. A quantitative and qualitative evaluation of llm-based explainable fault localization. Proceedings of the ACM on Software Engineering, 1(FSE):1424-1446, 2024. URL: https://doi.org/10.1145/3660771.
  7. Abdullah Khan, Rahul Nahar, Hao Chen, Gonzalo E Flores, and Can Li. Faultexplainer: Leveraging large language models for interpretable fault detection and diagnosis. arXiv preprint arXiv:2412.14492, 2024. Google Scholar
  8. Mattias Krysander, Jan Åslund, and Mattias Nyberg. An efficient algorithm for finding minimal overconstrained subsystems for model-based diagnosis. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 38(1):197-206, 2007. URL: https://doi.org/10.1109/TSMCA.2007.909555.
  9. Mattias Krysander, Jan Åslund, and Mattias Nyberg. An efficient algorithm for finding minimal overconstrained subsystems for model-based diagnosis. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 38(1):197-206, 2008. URL: https://doi.org/10.1109/TSMCA.2007.909555.
  10. Karol Kukla. jadlownik/FaultDiagnosis. Software, (visited on 2025-10-20). URL: https://github.com/jadlownik/FaultDiagnosis/tree/develop
    Software Heritage Logo archived version
    full metadata available at: https://doi.org/10.4230/artifacts.24965
  11. Lin Lin, Sihao Zhang, Song Fu, and Yikun Liu. Fd-llm: Large language model for fault diagnosis of complex equipment. Advanced Engineering Informatics, 65:103208, 2025. URL: https://doi.org/10.1016/J.AEI.2025.103208.
  12. Silke Merkelbach, Alexander Diedrich, Anna Sztyber-Betley, Louise Travé-Massuyès, Elodie Chanthery, Oliver Niggemann, and Roman Dumitrescu. Using multi-modal llms to create models for fault diagnosis. In The 35th International Conference on Principles of Diagnosis and Resilient Systems (DX'24), volume 125, 2024. Google Scholar
  13. Herbert Muehlburger and Franz Wotawa. Flex: Fault localization and explanation using open-source large language models in powertrain systems (short paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024), pages 25:1-25:14. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2024. URL: https://doi.org/10.4230/OASIcs.DX.2024.25.
  14. Herbert Mühlburger and Franz Wotawa. Faultlines-evaluating the efficacy of open-source large language models for fault detection in cyber-physical systems. In 2024 IEEE International Conference on Artificial Intelligence Testing (AITest), pages 47-54. IEEE, 2024. URL: https://doi.org/10.1109/AITEST62860.2024.00014.
  15. CG Pérez-Zuniga, E Chanthery, L Travé-Massuyès, and J Sotomayor. Fault-driven structural diagnosis approach in a distributed context. IFAC-PapersOnLine, 50(1):14254-14259, 2017. Google Scholar
  16. Raymond Reiter. A theory of diagnosis from first principles. Artificial intelligence, 32(1):57-95, 1987. URL: https://doi.org/10.1016/0004-3702(87)90062-2.
  17. Alicia Russell-Gilbert, Alexander Sommers, Andrew Thompson, Logan Cummins, Sudip Mittal, Shahram Rahimi, Maria Seale, Joseph Jaboure, Thomas Arnold, and Joshua Church. Aad-llm: Adaptive anomaly detection using large language models. In 2024 IEEE International Conference on Big Data (BigData), pages 4194-4203. IEEE, 2024. URL: https://doi.org/10.1109/BIGDATA62323.2024.10825679.
  18. Anna Sztyber Betley. asztyber/LLM_diagnostic_concepts. Software, (visited on 2025-10-20). URL: https://github.com/asztyber/LLM_diagnostic_concepts
    Software Heritage Logo archived version
    full metadata available at: https://doi.org/10.4230/artifacts.24966
  19. Laifa Tao, Haifei Liu, Guoao Ning, Wenyan Cao, Bohao Huang, and Chen Lu. Llm-based framework for bearing fault diagnosis. Mechanical Systems and Signal Processing, 224:112127, 2025. Google Scholar
  20. Louise Travé-Massuyes, Teresa Escobet, and Xavier Olive. Diagnosability analysis based on component-supported analytical redundancy relations. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 36(6):1146-1160, 2006. URL: https://doi.org/10.1109/TSMCA.2006.878984.
  21. Aidan ZH Yang, Claire Le Goues, Ruben Martins, and Vincent Hellendoorn. Large language models for test-free fault localization. In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, pages 1-12, 2024. Google Scholar
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact