Teaching Specific Scientific Knowledge into Large Language Models through Additional Training
This addresses the problem of integrating domain-specific knowledge into LLMs for scientific applications, but it is incremental as it builds on existing methods.
The researchers tackled embedding specialized scientific knowledge into the Llama 2 LLM through additional training, achieving partial success with a dataset of 65,000 papers but highlighting complexities and limitations.
Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives, especially in instructional formats. We utilize text augmentation to tackle the scarcity of specialized texts, including style conversions and translations. Hyperparameter optimization proves crucial, with different size models (7b, 13b, and 70b) reasonably undergoing additional training. Validating our methods, we construct a dataset of 65,000 scientific papers. Although we have succeeded in partially embedding knowledge, the study highlights the complexities and limitations of incorporating specialized information into LLMs, suggesting areas for further improvement.