How To Make AI Models More Accurate: Embrace Failure
IBM, Friday, June 13th, 2025
Fine-tuning on negative data produced a model well suited for chemistry, where successful experiments are rare. Failed experiments make chemical language models more accurate.
A negative result doesn't have to be a bad thing. In fact, a failed experiment can be as informative as a successful one.
Whether a chemistry experiment yields an unexpected product or no product at all, it offers new insights into the conditions that successful reactions require. And IBM Research scientists have shown that's also true for AI models.
A team of researchers trained a language model to predict chemical reactions, and it turned out it was more accurate when they tuned it on data from a mix of successful and unsuccessful chemistry experiments than it was when tuned on only successful experiments.