arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.01779cs.CLcs.AI
收藏

使用大型语言模型生成概念设计

Conceptual Design Generation Using Large Language Models

Autodesk Research(欧特克研究中心);University of California, Berkeley(加利福尼亚大学伯克利分校);Carnegie Mellon University(卡内基梅隆大学)

Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert

AI总结:

本文评估 LLM 生成概念设计的能力,针对 12 个设计问题结合专家与计算指标对比众包方案,并发现少样本提示可提升相似性。

摘要:

概念生成是概念设计阶段中的一个创造性步骤,设计师通常会借助头脑风暴、思维导图或众包设计创意来补充自身的领域知识。自然语言处理(NLP)和机器学习(ML)的最新进展推动了大型语言模型(LLM)的兴起,这些模型能够根据文本提示生成看似具有创造性的输出。这些模型的成功促使其在艺术、娱乐和其他创造性工作等多个领域中得到整合与应用。在本文中,我们利用 LLM 为一组 12 个设计问题生成解决方案,并将其与众包解决方案的基线进行比较。我们通过多个视角评估生成的设计解决方案与众包设计解决方案之间的差异,包括人类专家评估和计算指标。专家评估表明,LLM 生成的解决方案在平均可行性和实用性方面更高,而众包解决方案则更具新颖性。我们进行了提示工程实验,发现利用少样本学习可以生成与众包解决方案更相似的解决方案。这些发现为理解使用 LLM 生成的设计解决方案的质量提供了洞见,并开始评估提示工程技术;从业者可以利用这些技术,与 LLM 协同生成更高质量的设计解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑