AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing
This provides an accessible method for specializing large language models to the additive manufacturing domain, though it is incremental as it adapts existing techniques to a new application area.
The researchers developed AdditiveLLM2, a multi-modal large language model specialized for additive manufacturing by adapting the Gemma 3 model with domain-specific pretraining and instruction tuning on a 50-million-token dataset. The model achieved over 90% accuracy on additive manufacturing knowledge tasks.
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.