# PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID

arXiv: https://arxiv.org/abs/2607.18626 · HTML: https://mlsanity.com/paper/2607.18626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 21 Jul 2026.

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

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [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)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [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)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [PLAID: An Efficient Engine for Late Interaction Retrieval](https://mlsanity.com/paper/2205.09707/) (2022)
- [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)
- [Rethinking the Role of Token Retrieval in Multi-Vector Retrieval](https://mlsanity.com/paper/2304.01982/) (2023)
- [Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and Pitfalls](https://mlsanity.com/paper/2108.11044/) (2021)
- [Adaptive Re-Ranking with a Corpus Graph](https://mlsanity.com/paper/2208.08942/) (2022)
- [Generative Relevance Feedback with Large Language Models](https://mlsanity.com/paper/2304.13157/) (2023)
- [How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset](https://mlsanity.com/paper/2105.07975/) (2021)
- [Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard](https://mlsanity.com/paper/2306.07471/) (2023)
- [A Reproducibility Study of PLAID](https://mlsanity.com/paper/2404.14989/) (2024)
- [Lexically-Accelerated Dense Retrieval](https://mlsanity.com/paper/2307.16779/) (2023)
- [Quam: Adaptive Retrieval through Query Affinity Modelling](https://mlsanity.com/paper/2410.20286/) (2024)
- [Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models](https://mlsanity.com/paper/2503.14887/) (2025)
- [Breaking the Lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets](https://mlsanity.com/paper/2504.09353/) (2025)
- [LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback](https://mlsanity.com/paper/2504.01448/) (2025)

## Abstract (arXiv)

Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness. In this work, we introduce PLAID-PRF, a method that performs Pseudo-Relevance Feedback (PRF) over PLAID to reformulate ColBERT's query vectors based on the top-retrieved results. In contrast with prior methods that perform PRF on multi-vector retrieval models, PLAID-PRF keeps computational costs low by leveraging the internal PLAID centroid vectors, treating them similarly to tokens in traditional PRF methods. The method selects a small and diverse set of high-utility expansion vectors and appends them to the original query, rerunning PLAID to refine both candidate generation and final scoring. Extensive experiments on the standard in-domain MSMARCO and four out-of-domain BEIR benchmarks show that PLAID-PRF consistently improves retrieval effectiveness over various baselines. In particular, PLAID-PRF improves over PLAID by up to 4.3% nDCG@10 and 7.3% MRR@10, while introducing substantially less computation overhead than prior PRF methods. The results demonstrate that our proposed centroid-aware PRF method offers an effective and lightweight mechanism to improve the quality of top-ranked retrieved results. Overall, this work enables effective and efficient feedback-aware late-interaction retrieval without expensive query-time document-token clustering.