Path: A Machine Learning Method for Training Small-Scale (Under 100M Parameter) Neural Information Retrieval Models with as few as 10 Gold Relevance Labels

Researchers from the University of Waterloo, Stanford University, and IBM Research AI have introduced PATH – a method that uses prompts as auto-optimized training hyperparameters to train small-scale neural information retrieval models. This technique allows models with fewer than 100 million parameters to be trained with as few as ten gold relevance labels, generating high-quality synthetic training data. It demonstrates significant performance improvements, particularly noted on the BIRCO benchmark, outperforming larger models trained with much more labeled data.