AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing

TL;DR

AdditiveLLM2 is a multi-modal large language model tailored for additive manufacturing, combining domain-specific data and visual instruction tuning to achieve high accuracy in domain tasks.

Contribution

The paper introduces AdditiveLLM2, a novel multi-modal LLM specialized for additive manufacturing using a small, domain-specific dataset and visual instruction tuning.

Findings

Achieves over 90% accuracy in additive manufacturing tasks

Demonstrates effective domain adaptation with limited data

Proves proficiency in language and vision tasks

Abstract

This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.