# Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

arXiv: https://arxiv.org/abs/2106.11251 · HTML: https://mlsanity.com/paper/2106.11251/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2021.

## Built on by (most cited first, 30 of 32)

- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [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)
- [Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models](https://mlsanity.com/paper/2201.08471/) (2022)
- [Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges](https://mlsanity.com/paper/2403.00784/) (2024)
- [Contextual Document Embeddings](https://mlsanity.com/paper/2410.02525/) (2024)
- [A Study on Token Pruning for ColBERT](https://mlsanity.com/paper/2112.06540/) (2021)
- [Defending Against Disinformation Attacks in Open-Domain Question Answering](https://mlsanity.com/paper/2212.10002/) (2022)
- [Taxonomy-guided Semantic Indexing for Academic Paper Search](https://mlsanity.com/paper/2410.19218/) (2024)
- [Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy](https://mlsanity.com/paper/2403.04160/) (2024)
- [Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking](https://mlsanity.com/paper/2505.21815/) (2025)
- [Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search](https://mlsanity.com/paper/2212.09017/) (2022)
- [A Reproducibility Study of PLAID](https://mlsanity.com/paper/2404.14989/) (2024)
- [Optimizing Test-Time Query Representations for Dense Retrieval](https://mlsanity.com/paper/2205.12680/) (2022)
- [Constructing and Evaluating Declarative RAG Pipelines in PyTerrier](https://mlsanity.com/paper/2506.10802/) (2025)
- [Relevance Feedback with Brain Signals](https://mlsanity.com/paper/2312.05669/) (2023)
- [Collective Relevance Labeling for Passage Retrieval](https://mlsanity.com/paper/2205.03273/) (2022)
- [A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback](https://mlsanity.com/paper/2511.17255/) (2025)
- [Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://mlsanity.com/paper/2601.07782/) (2026)
- [LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback](https://mlsanity.com/paper/2504.01448/) (2025)
- [LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2204.11545/) (2022)
- [Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems](https://mlsanity.com/paper/2206.12993/) (2022)
- [Learned Accelerator Framework for Angular-Distance-Based High-Dimensional DBSCAN](https://mlsanity.com/paper/2302.03136/) (2023)
- [Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders](https://mlsanity.com/paper/2405.03651/) (2024)
- [GEM: A Native Graph-based Index for Multi-Vector Retrieval](https://mlsanity.com/paper/2603.20336/) (2026)
- [Online Distillation for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2306.09657/) (2023)
- [Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap](https://mlsanity.com/paper/2501.14826/) (2025)
- [ConceptCarve: Dynamic Realization of Evidence](https://mlsanity.com/paper/2504.07228/) (2025)
- [Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation](https://mlsanity.com/paper/2506.23662/) (2025)
- [Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades](https://mlsanity.com/paper/2510.16393/) (2025)

## Abstract (arXiv)

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the pseudo-relevant set. Recently, dense retrieval -- through the use of neural contextual language models such as BERT for analysing the documents' and queries' contents and computing their relevance scores -- has shown a promising performance on several information retrieval tasks still relying on the traditional inverted index for identifying documents relevant to a query. Two different dense retrieval families have emerged: the use of single embedded representations for each passage and query (e.g. using BERT's [CLS] token), or via multiple representations (e.g. using an embedding for each token of the query and document). In this work, we conduct the first study into the potential for multiple representation dense retrieval to be enhanced using pseudo-relevance feedback. In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, we extract representative feedback embeddings (using KMeans clustering) -- while ensuring that these embeddings discriminate among passages (based on IDF) -- which are then added to the query representation. These additional feedback embeddings are shown to both enhance the effectiveness of a reranking as well as an additional dense retrieval operation. Indeed, experiments on the MSMARCO passage ranking dataset show that MAP can be improved by upto 26% on the TREC 2019 query set and 10% on the TREC 2020 query set by the application of our proposed ColBERT-PRF method on a ColBERT dense retrieval approach.