Abstract
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.
Recommended Citation
I. Mackie et al., "GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval,", Jun 2023.
Department(s)
Computer Science
Keywords and Phrases
Text Generation; Document Retrieval; Relevance Modeling
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Publication Date
June 16, 2023
