Pseudo Relevance Feedback Is Enough To Close The Gap Between Small And Large Dense Retrieval Models

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2025pseudo

Related papers

• Improving Query Representations For Dense Retrieval With Pseudo Relevance Feedback: A Reproducibility Study (2021)7.16
• TPRF: A Transformer-based Pseudo-relevance Feedback Model For Efficient And Effective Retrieval (2024)0.00
• A Deep Learning Approach For Selective Relevance Feedback (2024)6.34
• Making Large Language Models Efficient Dense Retrievers (2025)0.00
• Scalingnote: Scaling Up Retrievers With Large Language Models For Real-world Dense Retrieval (2024)0.00
• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25
• Pseudo-relevance Feedback For Multiple Representation Dense Retrieval (2021)12.93
• Promptreps: Prompting Large Language Models To Generate Dense And Sparse Representations For Zero-shot Document Retrieval (2024)10.61