# Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval

arXiv: https://arxiv.org/abs/2305.07477 · HTML: https://mlsanity.com/paper/2305.07477/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2023.

## Built on by (most cited first, 9 of 9)

- [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)
- [Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM](https://mlsanity.com/paper/2312.15450/) (2023)
- [Guiding Retrieval using LLM-based Listwise Rankers](https://mlsanity.com/paper/2501.09186/) (2025)
- [Meta Knowledge for Retrieval Augmented Large Language Models](https://mlsanity.com/paper/2408.09017/) (2024)
- [Test-time Corpus Feedback: From Retrieval to RAG](https://mlsanity.com/paper/2508.15437/) (2025)
- [A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry](https://mlsanity.com/paper/2502.08557/) (2025)
- [QueStER: Query Specification for Generative keyword-based Retrieval](https://mlsanity.com/paper/2511.05301/) (2025)
- [Test-Time Compute for Frozen Embedding Models through Agentic Program Search](https://mlsanity.com/paper/2605.11374/) (2026)

## Abstract (arXiv)

Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansion models using text generated from large language models can improve sparse retrieval without depending on first-pass retrieval effectiveness. This work extends GRF to dense and learned sparse retrieval paradigms with experiments over six standard document ranking benchmarks. We find that GRF improves over comparable PRF techniques by around 10% on both precision and recall-oriented measures. Nonetheless, query analysis shows that GRF and PRF have contrasting benefits, with GRF providing external context not present in first-pass retrieval, whereas PRF grounds the query to the information contained within the target corpus. Thus, we propose combining generative and pseudo-relevance feedback ranking signals to achieve the benefits of both feedback classes, which significantly increases recall over PRF methods on 95% of experiments.