Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules

We evaluate the effectiveness of fine-tuning GPT-3 for the prediction of electronic and functional properties of organic molecules. Our findings show that fine-tuned GPT-3 can successfully identify and distinguish between chemically meaningful patterns, and discern subtle differences among them, exhibiting robust predictive performance for the prediction of molecular properties. We focus on assessing the fine-tuned models' resilience to information loss, resulting from the absence of atoms or chemical groups, and to noise that we introduce via random alterations in atomic identities. We discuss the challenges and limitations inherent to the use of GPT-3 in molecular machine-learning tasks and suggest potential directions for future research and improvements to address these issues.

Automated summary

We evaluate the effectiveness of fine-tuning GPT-3 for predicting electronic and functional properties of organic molecules. The findings demonstrate that the fine-tuned GPT-3 can successfully identify meaningful chemical patterns and discern subtle differences among them, exhibiting robust predictive performance for molecular properties. The study also discusses the challenges and limitations of using GPT-3 in molecular machine learning tasks and suggests potential directions for future research and improvements.