# Generative Design Ideation: A Natural Language Generation Approach

arXiv: https://arxiv.org/abs/2204.09658 · HTML: https://mlsanity.com/paper/2204.09658/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [TechNet: Technology Semantic Network Based on Patent Data](https://mlsanity.com/paper/1906.00411/) (2019)
- [Data-Driven Innovation: What Is It](https://mlsanity.com/paper/2201.08184/) (2022)

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

- [ChatGPT and Other Large Language Models as Evolutionary Engines for Online Interactive Collaborative Game Design](https://mlsanity.com/paper/2303.02155/) (2023)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers](https://mlsanity.com/paper/2212.13196/) (2022)
- [Large Language Model for Patent Concept Generation](https://mlsanity.com/paper/2409.00092/) (2024)
- [The Innovation Paradox: Concept Space Expansion with Diminishing Originality and the Promise of Creative AI](https://mlsanity.com/paper/2303.13300/) (2023)

## Abstract (arXiv)

This paper aims to explore a generative approach for knowledge-based design ideation by applying the latest pre-trained language models in artificial intelligence (AI). Specifically, a method of fine-tuning the generative pre-trained transformer using the USPTO patent database is proposed. The AI-generated ideas are not only in concise and understandable language but also able to synthesize the target design with external knowledge sources with controllable knowledge distance. The method is tested in a case study of rolling toy design and the results show good performance in generating ideas of varied novelty with near-field and far-field source knowledge.