EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Graph retrieval-augmented generation for enhancing LLM-based ML algorithm recommendation in product development

Sebastian Sonntag, Adrian Dörnbach, Arun Nagarajah

Proceedings of the Design Society · 2026-08 · 6 · 2551-2560

DOI: 10.1017/pds.2026.10613 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Sebastian Sonntag und 2 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in machine learning (ML) offer substantial potential for product development (PD), yet adoption remains limited. A crucial step is identifying suitable ML algorithms for a given PD problem, which requires translating domain-specific formulations into appropriate ML tasks. Prior work indicates that LLMs struggle with this step due to insufficient domain knowledge. Therefore, this study investigates whether a domain-specific GraphRAG approach improves model performance by enriching prompts with structured context from a PD knowledge graph.

Zitieren

APA

Sonntag, S., Dörnbach, A., & Nagarajah, A. (2026). Graph retrieval-augmented generation for enhancing LLM-based ML algorithm recommendation in product development. Proceedings of the Design Society, 6, 2551-2560. https://doi.org/10.1017/pds.2026.10613

Vancouver

Sonntag S, Dörnbach A, Nagarajah A. Graph retrieval-augmented generation for enhancing LLM-based ML algorithm recommendation in product development. Proceedings of the Design Society. 2026;6:2551-2560. doi:10.1017/pds.2026.10613

BibTeX
@article{Sonntag2026,
  author = {Sonntag, Sebastian and Dörnbach, Adrian and Nagarajah, Arun},
  title = {Graph retrieval-augmented generation for enhancing LLM-based ML algorithm recommendation in product development},
  journal = {Proceedings of the Design Society},
  year = {2026},
  volume = {6},
  pages = {2551--2560},
  doi = {10.1017/pds.2026.10613}
}
Kostenlos starten →