Queryable Microarchitecture Knowledge Base using Retrieval-Augmented Generation
DOI:
https://doi.org/10.64552/wipiec.v11i1.95Keywords:
Embedded systems, information extraction, retrieval-augmented generationAbstract
Microarchitecture documentation, such as datasheets and user manuals, is indispensable for embedded software development. However, the extensive volume and complexity of these documents render information retrieval a time- and effort-intensive task. To address this challenge, we propose a framework for constructing a queryable knowledge base on microarchitecture documentation, leveraging Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs). As a proof of concept, we implement a knowledge base on AURIX TriCore TC27x documentation and evaluate this knowledge base by querying it with a curated set of questions. The generated responses are evaluated by measuring their semantic similarity to reference answers. In our evaluation, we assess the performance of six LLMs with different model architectures and sizes. The results show that the smaller models (with 8 billion and 3 billion parameters) achieve similarity scores comparable to those of the larger model (with 72 billion parameters). These initial findings demonstrate the robustness of our framework for creating queryable knowledge bases and the potential of smaller LLMs for efficient information retrieval in this context
References
P. Lewis et al., ‘Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks’, in Advances in Neural Information Processing Systems, 2020, vol. 33.
V. Ashish et al., ‘Attention is all you need’, Advances in neural information processing systems, vol. 30, p. I, 2017.
‘AURIX TC27x D-Step 32-bit Single-Chip Microcontroller User Manual v2.2’, Infineon Technologies AG.
‘PyPDF2’. [Online]. Available: https://pypdf2.readthedocs.io/en/3.x/
‘Sentence-Transformer Model: all-MiniLM-L6-v2’. [Online]. Available: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
M. Douze et al., ‘The FAISS library’, arXiv preprint arXiv:2401. 08281, 2024.
W. Zhilin et al., ‘HelpSteer2-Preference: Complementing Ratings with Preferences’, arXiv [cs.LG]. 2024.
Q. Team, ‘Qwen2.5: A Party of Foundation Models’. Sep-2024. Available: https://qwenlm.github.io/blog/qwen2.5/
A. Grattafiori et al., ‘The llama 3 herd of models’, arXiv preprint arXiv:2407. 21783, 2024.
Nvidia, ‘LLM Benchmarking: Fundamental Concepts’. [Online]. Available: https://developer.nvidia.com/blog/llm-benchmarking-fundamental-concepts/.
T. Zhang and Others, ‘Bertscore: Evaluating text generation with bert’, arXiv preprint arXiv:1904. 09675, 2019.
N. Reimers and I. Gurevych, ‘Sentence-bert: Sentence embeddings using siamese bert-networks’, arXiv preprint arXiv:1908. 10084, 2019. DOI: https://doi.org/10.18653/v1/D19-1410
DeepSeek-AI, ‘DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning’, arXiv [cs.CL]. 2025.
M. Arslan et al., ‘A Survey on RAG with LLMs’, Procedia Computer Science, vol. 246, pp. 3781–3790, 2024. DOI: https://doi.org/10.1016/j.procs.2024.09.178
Y. Gao et al., ‘Retrieval-augmented generation for Large Language Models: A survey’, arXiv preprint arXiv:2312. 10997, vol. 2, p. 1, 2023.
R. Chen et al., ‘Retrieval-Augmented Generation with Knowledge Graphs: A Survey’, in Computer Science Undergradaute Conference 2025@ XJTU.
S. Yadav, ‘AeroQuery RAG and LLM for Aerospace Query in Designs, Development, Standards, Certifications’, in 2024 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2024, pp. 1–6. DOI: https://doi.org/10.1109/CONECCT62155.2024.10677028
B. Hernandez-Salinas et al., ‘IDAS: Intelligent Driving Assistance System using RAG’, IEEE Open Journal of Vehicular Technology, 2024. DOI: https://doi.org/10.1109/OJVT.2024.3447449
K. Kieu et al., ‘Empowering Automotive Software Development with LLM-RAG Integration’, 2024.
M. Simoni et al., ‘Morse: Bridging the gap in cybersecurity expertise with retrieval augmented generation’, in Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, 2025, pp. 1213–1222. DOI: https://doi.org/10.1145/3672608.3707898
B. V. Balu et al., ‘Towards Automated Safety Requirements Derivation Using Agent-based RAG’, arXiv preprint arXiv:2504. 11243, 2025. DOI: https://doi.org/10.1609/aaaiss.v5i1.35605
K. Kurniawan et al., ‘CyKG-RAG: Towards knowledge-graph enhanced retrieval augmented generation for cybersecurity’, 2024.
Z. Lu et al., ‘HSG-RAG: Hierarchical Knowledge Base Construction for Embedded System Development’, ACM Transactions on Design Automation of Electronic Systems.
F. Liu et al., ‘Enhancing Automotive PDF Chatbots: A Graph RAG Approach with Custom Function Calling for Locally Deployed Ollama Models’, in Proceedings of the 2024 International Conference on Artificial Intelligence, Digital Media Technology and Interaction Design, 2024, pp. 6–13. DOI: https://doi.org/10.1145/3726010.3726012
Y. Ojima et al., ‘Knowledge Management for Automobile Failure Analysis Using Graph RAG’, in 2024 IEEE International Conference on Big Data (BigData), 2024, pp. 6624–663 DOI: https://doi.org/10.1109/BigData62323.2024.10826046
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Vignesh Manjunath, Jesus Pestana, Tobias Scheipel, Marcel Baunach
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
License Terms:
Except where otherwise noted, content on this website is lincesed under a Creative Commons Attribution Non-Commercial License (CC BY NC)
Use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes, is permitted.
Copyright to any article published by WiPiEC retained by the author(s). Authors grant WiPiEC Journal a license to publish the article and identify itself as the original publisher. Authors also grant any third party the right to use the article freely as long as it is not used for commercial purposes and its original authors, citation details, and publisher are identified, in accordance with CC BY NC license. Fore more information on license terms, click here.