Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs can generate irrelevant information that harms retrieval effectiveness. To address this, we propose Generative Relevance Modeling (GRM) that uses Relevance-Aware Sample Estimation (RASE) for more accurate weighting of expansion terms. Specifically, we identify similar real documents for each generated document and use a neural re-ranker to estimate their relevance. Experiments on three standard document ranking benchmarks show that GRM improves MAP by 6-9% and R@1k by 2-4%, surpassing previous methods.
@article{arxiv.2306.09938,
title = {GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval},
author = {Iain Mackie and Ivan Sekulic and Shubham Chatterjee and Jeffrey Dalton and Fabio Crestani},
journal= {arXiv preprint arXiv:2306.09938},
year = {2023}
}