# GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval

arXiv: https://arxiv.org/abs/2306.09938 · HTML: https://mlsanity.com/paper/2306.09938/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2023.

## Built on by (most cited first, 3 of 3)

- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval](https://mlsanity.com/paper/2310.20158/) (2023)
- [TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework](https://mlsanity.com/paper/2511.05385/) (2025)

## Abstract (arXiv)

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.