# Retrieval Augmented Generation using Engineering Design Knowledge

arXiv: https://arxiv.org/abs/2307.06985 · HTML: https://mlsanity.com/paper/2307.06985/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 13 Jul 2023.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 6 of 6)

- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Engineering Knowledge Graph from Patent Database](https://mlsanity.com/paper/2106.06739/) (2021)
- [Natural Language Processing in-and-for Design Research](https://mlsanity.com/paper/2111.13827/) (2021)
- [Guiding Data-Driven Design Ideation by Knowledge Distance](https://mlsanity.com/paper/2210.10104/) (2022)
- [Enhancing Patent Retrieval using Text and Knowledge Graph Embeddings: A Technical Note](https://mlsanity.com/paper/2211.01976/) (2022)

## Built on by (most cited first, 5 of 5)

- [Retrieval-Augmented Generation for Mobile Edge Computing via Large Language Model](https://mlsanity.com/paper/2412.20820/) (2024)
- [Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation](https://mlsanity.com/paper/2507.19771/) (2025)
- [Linguistic and Structural Basis of Engineering Design Knowledge](https://mlsanity.com/paper/2312.06355/) (2023)
- [Tripl`etoile: Extraction of Knowledge from Microblogging Text](https://mlsanity.com/paper/2408.14908/) (2024)
- [Optimizing Retrieval-Augmented Generation for Electrical Engineering: A Case Study on ABB Circuit Breakers](https://mlsanity.com/paper/2505.17520/) (2025)

## Abstract (arXiv)

Aiming to support Retrieval Augmented Generation (RAG) in the design process, we present a method to identify explicit, engineering design facts - {head entity :: relationship :: tail entity} from patented artefact descriptions. Given a sentence with a pair of entities (based on noun phrases) marked in a unique manner, our method extracts the relationship that is explicitly communicated in the sentence. For this task, we create a dataset of 375,084 examples and fine-tune language models for relation identification (token classification) and elicitation (sequence-to-sequence). The token classification approach achieves up to 99.7 % accuracy. Upon applying the method to a domain of 4,870 fan system patents, we populate a knowledge base of over 2.93 million facts. Using this knowledge base, we demonstrate how Large Language Models (LLMs) are guided by explicit facts to synthesise knowledge and generate technical and cohesive responses when sought out for knowledge retrieval tasks in the design process.