# LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback

arXiv: https://arxiv.org/abs/2504.01448 · HTML: https://mlsanity.com/paper/2504.01448/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [Query Expansion by Prompting Large Language Models](https://mlsanity.com/paper/2305.03653/) (2023)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [RepBERT: Contextualized Text Embeddings for First-Stage Retrieval](https://mlsanity.com/paper/2006.15498/) (2020)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval](https://mlsanity.com/paper/2106.11251/) (2021)
- [PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval](https://mlsanity.com/paper/2404.18424/) (2024)
- [Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and Pitfalls](https://mlsanity.com/paper/2108.11044/) (2021)
- [Generative Relevance Feedback with Large Language Models](https://mlsanity.com/paper/2304.13157/) (2023)
- [Leveraging LLMs for Unsupervised Dense Retriever Ranking](https://mlsanity.com/paper/2402.04853/) (2024)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study](https://mlsanity.com/paper/2112.06400/) (2021)
- [TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking](https://mlsanity.com/paper/2403.17759/) (2024)
- [Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval](https://mlsanity.com/paper/2308.08285/) (2023)
- [PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer](https://mlsanity.com/paper/2101.07918/) (2021)

## Built on by (most cited first, 2 of 2)

- [Test-Time Compute for Frozen Embedding Models through Agentic Program Search](https://mlsanity.com/paper/2605.11374/) (2026)
- [PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID](https://mlsanity.com/paper/2607.18626/) (2026)

## Abstract (arXiv)

Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large Language Model (LLM) based dense retrievers. We introduce LLM-VPRF and evaluate its effectiveness across multiple benchmark datasets, analyzing how different LLMs impact the feedback mechanism. Our results demonstrate that VPRF's benefits successfully extend to LLM architectures, establishing it as a robust technique for enhancing dense retrieval performance regardless of the underlying models. This work bridges the gap between VPRF with traditional BERT-based dense retrievers and modern LLMs, while providing insights into their future directions.