BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Du, Yuhao, Chen, Shunian, Zan, Wenbo, Li, Peizhao, Wang, Mingxuan, Song, Dingjie, Li, Bo, Hu, Yan, Wang, Benyou
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913618145050624
author Du, Yuhao
Chen, Shunian
Zan, Wenbo
Li, Peizhao
Wang, Mingxuan
Song, Dingjie
Li, Bo
Hu, Yan
Wang, Benyou
author_facet Du, Yuhao
Chen, Shunian
Zan, Wenbo
Li, Peizhao
Wang, Mingxuan
Song, Dingjie
Li, Bo
Hu, Yan
Wang, Benyou
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2412_14203
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement
Du, Yuhao
Chen, Shunian
Zan, Wenbo
Li, Peizhao
Wang, Mingxuan
Song, Dingjie
Li, Bo
Hu, Yan
Wang, Benyou
Human-Computer Interaction
Artificial Intelligence
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
title BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2412.14203