HoneyBee: Intel Labs and Mila’s Novel Language Model
By working together, Intel Labs and the Bang Liu group at Mila have developed HoneyBee, a cutting-edge large language model (LLM) specialized to materials science that is currently available on Hugging Face
This builds on Intel and the Mila – Quebec AI Institute’s ongoing research efforts to develop novel AI tools for materials discovery to address challenges like climate change and sustainable semiconductor manufacturing
According to they partnership between Intel Labs and Mila on the MatSci-NLP article and blog, materials science is an intricate multidisciplinary area that aims to comprehend matter’s interaction in order to efficiently
The opportunity to develop specialized scientific LLMs that can comprehend specialized material, such chemical and mathematical formulas, as well as domain-specific scientific language is made possible by the abundance of research literature and textual information found in various
The difficulty is exacerbated by the fact that a large portion of scientific knowledge is expressed in language peculiar to a particular scientific field and has exact meanings within those contexts
Large-scale learning models (LLMs) have demonstrated emergent ability in domains where they were not trained at first, and instruction-based fine-tuning can help them become even more proficient in particular domains
HoneyBee language models are trained on verifiable data and subsequently assessed by the Evaluator (GPT-4), another independent LLM