Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels
This addresses the data scarcity problem in information retrieval for researchers and practitioners, offering a more efficient training approach.
The researchers tackled the problem of training neural information retrieval models with minimal labeled data by developing a method that automatically optimizes language model prompts for synthetic query generation, achieving performance competitive with 7B-parameter models trained on over 100K labels using only 10 gold labels.
We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels. The method depends on generating synthetic queries for documents using a language model (LM), and the key step is that we automatically optimize the LM prompt that is used to generate these queries based on training quality. In experiments with the BIRCO benchmark, we find that models trained with our method outperform RankZephyr and are competitive with RankLLama, both of which are 7B parameter models trained on over 100K labels. These findings point to the power of automatic prompt optimization for synthetic dataset generation.