EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuning

Saiful Islam Sagor, Tania Haghighi, Md Rahatuzzaman, Anasheh Khecho, Minhaj Nur Alam, Jacob Zorn, Erina Baynojir Joyee

Frontiers in Manufacturing Technology · 21.07.2026 · 6

DOI: 10.3389/fmtec.2026.1875357 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Manufacturing Technology, online erschienen am 21.07.2026. Verfasst von Saiful Islam Sagor und 6 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

General-purpose large language models (LLMs) often struggle to generate reliable responses in specialized engineering domains due to limited domain grounding and insufficient exposure to structured technical knowledge. This study investigates practical strategies for adapting a foundation LLM to the additive manufacturing (AM) domain in order to improve answer accuracy, relevance and usability for expert-level question answering. AM knowledge is distributed across heterogeneous sources such as academic literature, manufacturer documentation, technical standards and procedural guides. Although general LLMs demonstrate strong linguistic capabilities, they frequently fail to retrieve and contextualize such domain-specific information. Two common approaches to address this limitation are domain-specific fine-tuning and retrieval-augmented generation (RAG).

Methods

A curated AM corpus is constructed and used to evaluate three configurations based on LLaMA-3-8B: (1) a pretrained baseline model, (2) a RAG system that retrieves relevant document chunks from a vector database and (3) a model fine-tuned on raw domain text using quantized low-rank adaptation (QLoRA). Performance is evaluated using 200 expert-designed AM questions assessed by mechanical engineering experts for accuracy, relevance and overall preference.

Results

The RAG model consistently outperforms the baseline. Among the 200 questions, 75.5% of RAG responses are judged more accurate, 85.2% are preferred overall and 90.8% are rated more relevant than baseline responses. In contrast, fine-tuning on raw AM text reduces performance, producing more accurate answers in only 5.6% of cases and more relevant answers in 32.5% of cases.

Discussion

These results indicate that retrieval-augmented approaches provide a more effective pathway for adapting LLMs to specialized engineering domains than naive fine-tuning on unstructured technical data. RAG grounds responses in retrieved source documents at inference time, enabling higher accuracy and relevance without requiring model retraining.

Zitieren

APA

Sagor, S. I., Haghighi, T., Rahatuzzaman, M., Khecho, A., Alam, M. N., Zorn, J., & Joyee, E. B. (2026). Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuning. Frontiers in Manufacturing Technology, 6. https://doi.org/10.3389/fmtec.2026.1875357

Vancouver

Sagor SI, Haghighi T, Rahatuzzaman M, Khecho A, Alam MN, Zorn J, et al. Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuning. Frontiers in Manufacturing Technology. 2026;6. doi:10.3389/fmtec.2026.1875357

BibTeX
@article{Sagor2026,
  author = {Sagor, Saiful Islam and Haghighi, Tania and Rahatuzzaman, Md and Khecho, Anasheh and Alam, Minhaj Nur and Zorn, Jacob and Joyee, Erina Baynojir},
  title = {Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuning},
  journal = {Frontiers in Manufacturing Technology},
  year = {2026},
  volume = {6},
  doi = {10.3389/fmtec.2026.1875357}
}
Kostenlos starten →