Generative Relevance Feedback with Large Language Models
Authors:
- Iain MackieIMIain Mackie
- Shubham ChatterjeeSCShubham Chatterjee
- Jeffrey DaltonJDJeffrey Dalton
Preprint
Abstract
Current query expansion models use pseudo-relevance feedback to improve first-pass retrieval effectiveness; however, this fails when the initial results are not relevant. Instead of building a language model from retrieved results, we propose Generative Relevance Feedback (GRF) that builds probabilistic feedback models from long-form text generated from Large Language Models. We study the effective methods for generating text by varying the zero-shot generation subtasks: queries, entities, facts, news articles, documents, and essays. We evaluate GRF on document retrieval benchmarks covering a diverse set of queries and document collections, and the results show that GRF methods significantly outperform previous PRF methods. Specifically, we improve MAP between 5-19% and NDCG@10 17-24% compared to RM3 expansion, and achieve the best R@1k effectiveness on all datasets compared to state-of-the-art sparse, dense, and expansion models.Keywords
All Related Versions
- Version 1, 2023-04-25, ArXiv
- Published version: , 2026.
This publication has 7 references indexed in Scilit:
- Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and PitfallsACM Transactions on Information Systems, 2023
- ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document RetrievalACM Transactions on the Web, 2023
- Pretrained Transformers for Text Ranking: BERT and Beyond2021
- Query Expansion with Freebase2015
- Conceptual language models for domain-specific retrievalInformation Processing & Management, 2010
- Query dependent pseudo-relevance feedback based on wikipedia2009
- UMass at TREC 2004: Novelty and HARD2004