用自迭代训练法提升大模型生成精准CAD脚本的能力
BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement
- 通过自改进机制逐步优化模型生成能力
- 在自定义数据集上实现高准确率的脚本生成
- 适合从事智能设计自动化的研究者与工程师
大型语言模型（LLM）在计算机辅助设计（CAD）领域的应用仍属空白。本文提出BlenderLLM，一种专为CAD任务设计的自改进训练框架。为此，我们构建了专属训练数据集BlendNet，并开发了全面评估工具CADBench。实验表明，现有模型在生成准确的CAD脚本方面存在显著局限。而通过少量指令微调与迭代自改进，BlenderLLM在功能性和脚本生成准确性上均显著优于现有模型。该研究为LLM在CAD中的应用奠定基础，展示了自改进模型在推动CAD自动化方面的巨大潜力。数据集、模型、基准和源代码已公开于https://github.com/FreedomIntelligence/BlenderLLM。
原文摘要 · Abstract (English)
The application of Large Language Models (LLMs) in Computer-Aided Design (CAD) remains an underexplored area, despite their remarkable advancements in other domains. In this paper, we present BlenderLLM, a novel framework for training LLMs specifically for CAD tasks leveraging a self-improvement methodology. To support this, we developed a bespoke training dataset, BlendNet, and introduced a comprehensive evaluation suite, CADBench. Our results reveal that existing models demonstrate significant limitations in generating accurate CAD scripts. However, through minimal instruction-based fine-tuning and iterative self-improvement, BlenderLLM significantly surpasses these models in both functionality and accuracy of CAD script generation. This research establishes a strong foundation for the application of LLMs in CAD while demonstrating the transformative potential of self-improving models in advancing CAD automation. We encourage further exploration and adoption of these methodologies to drive innovation in the field. The dataset, model, benchmark, and source code are publicly available at https://github.com/FreedomIntelligence/BlenderLLM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。