# Conceptual Design Generation Using Large Language Models

arXiv: https://arxiv.org/abs/2306.01779 · HTML: https://mlsanity.com/paper/2306.01779/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 69 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [Automatic Generation of Programming Exercises and Code Explanations using Large Language Models](https://mlsanity.com/paper/2206.11861/) (2022)
- [The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues](https://mlsanity.com/paper/2205.07540/) (2022)
- [CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis](https://mlsanity.com/paper/2103.06242/) (2021)
- [Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design](https://mlsanity.com/paper/2302.02913/) (2023)
- [Generative Transformers for Design Concept Generation](https://mlsanity.com/paper/2211.03468/) (2022)
- [Neural Machine Translation: A Review of Methods, Resources, and Tools](https://mlsanity.com/paper/2012.15515/) (2020)
- [3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders](https://mlsanity.com/paper/1904.07964/) (2019)
- [Generative Pre-Trained Transformer for Design Concept Generation: An Exploration](https://mlsanity.com/paper/2111.08489/) (2021)
- [Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers](https://mlsanity.com/paper/2212.13196/) (2022)
- [Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces](https://mlsanity.com/paper/2110.03760/) (2021)

## Built on by (most cited first, 13 of 13)

- [Query2CAD: Generating CAD models using natural language queries](https://mlsanity.com/paper/2406.00144/) (2024)
- ['Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants](https://mlsanity.com/paper/2409.19430/) (2024)
- [Elicitron: An LLM Agent-Based Simulation Framework for Design Requirements Elicitation](https://mlsanity.com/paper/2404.16045/) (2024)
- [CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation](https://mlsanity.com/paper/2603.26512/) (2026)
- [AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Models](https://mlsanity.com/paper/2403.13002/) (2024)
- [Opportunities for Large Language Models and Discourse in Engineering Design](https://mlsanity.com/paper/2306.09169/) (2023)
- [Language Models as Critical Thinking Tools: A Case Study of Philosophers](https://mlsanity.com/paper/2404.04516/) (2024)
- [Inspired by AI? A Novel Generative AI System To Assist Conceptual Automotive Design](https://mlsanity.com/paper/2407.11991/) (2024)
- [Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark](https://mlsanity.com/paper/2505.17512/) (2025)
- [An Artificial Intelligence Approach for Interpreting Creative Combinational Designs](https://mlsanity.com/paper/2405.04985/) (2024)
- [A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction](https://mlsanity.com/paper/2505.21109/) (2025)
- [Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case](https://mlsanity.com/paper/2603.20151/) (2026)
- [Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework](https://mlsanity.com/paper/2606.21378/) (2026)

## Abstract (arXiv)

Concept generation is a creative step in the conceptual design phase, where designers often turn to brainstorming, mindmapping, or crowdsourcing design ideas to complement their own knowledge of the domain. Recent advances in natural language processing (NLP) and machine learning (ML) have led to the rise of Large Language Models (LLMs) capable of generating seemingly creative outputs from textual prompts. The success of these models has led to their integration and application across a variety of domains, including art, entertainment, and other creative work. In this paper, we leverage LLMs to generate solutions for a set of 12 design problems and compare them to a baseline of crowdsourced solutions. We evaluate the differences between generated and crowdsourced design solutions through multiple perspectives, including human expert evaluations and computational metrics. Expert evaluations indicate that the LLM-generated solutions have higher average feasibility and usefulness while the crowdsourced solutions have more novelty. We experiment with prompt engineering and find that leveraging few-shot learning can lead to the generation of solutions that are more similar to the crowdsourced solutions. These findings provide insight into the quality of design solutions generated with LLMs and begins to evaluate prompt engineering techniques that could be leveraged by practitioners to generate higher-quality design solutions synergistically with LLMs.