# Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models

arXiv: https://arxiv.org/abs/2503.14887 · HTML: https://mlsanity.com/paper/2503.14887/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [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)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval](https://mlsanity.com/paper/2312.15503/) (2023)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [BERT-QE: Contextualized Query Expansion for Document Re-ranking](https://mlsanity.com/paper/2009.07258/) (2020)
- [Generative Query Reformulation for Effective Adhoc Search](https://mlsanity.com/paper/2308.00415/) (2023)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study](https://mlsanity.com/paper/2112.06400/) (2021)
- [To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers](https://mlsanity.com/paper/2205.00235/) (2022)
- [How does Feedback Signal Quality Impact Effectiveness of Pseudo Relevance Feedback for Passage Retrieval?](https://mlsanity.com/paper/2205.05888/) (2022)

## Built on by (most cited first, 4 of 4)

- [PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing](https://mlsanity.com/paper/2508.11116/) (2025)
- [Test-Time Compute for Frozen Embedding Models through Agentic Program Search](https://mlsanity.com/paper/2605.11374/) (2026)
- [Test-Time Training for Zero-Resource Dense Retrieval Reranking](https://mlsanity.com/paper/2606.01070/) (2026)
- [PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID](https://mlsanity.com/paper/2607.18626/) (2026)

## Abstract (arXiv)

Scaling dense retrievers to larger large language model (LLM) backbones has been a dominant strategy for improving their retrieval effectiveness. However, this has substantial cost implications: larger backbones require more expensive hardware (e.g. GPUs with more memory) and lead to higher indexing and querying costs (latency, energy consumption). In this paper, we challenge this paradigm by introducing PromptPRF, a feature-based pseudo-relevance feedback (PRF) framework that enables small LLM-based dense retrievers to achieve effectiveness comparable to much larger models. PromptPRF uses LLMs to extract query-independent, structured and unstructured features (e.g., entities, summaries, chain-of-thought keywords, essay) from top-ranked documents. These features are generated offline and integrated into dense query representations via prompting, enabling efficient retrieval without additional training. Unlike prior methods such as GRF, which rely on online, query-specific generation and sparse retrieval, PromptPRF decouples feedback generation from query processing and supports dense retrievers in a fully zero-shot setting. Experiments on TREC DL and BEIR benchmarks demonstrate that PromptPRF consistently improves retrieval effectiveness and offers favourable cost-effectiveness trade-offs. We further present ablation studies to understand the role of positional feedback and analyse the interplay between feature extractor size, PRF depth, and model performance. Our findings demonstrate that with effective PRF design, scaling the retriever is not always necessary, narrowing the gap between small and large models while reducing inference cost.