# NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

arXiv: https://arxiv.org/abs/1810.12936 · HTML: https://mlsanity.com/paper/1810.12936/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2018.

## Built on by (most cited first, 17 of 17)

- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [Contextual Document Embeddings](https://mlsanity.com/paper/2410.02525/) (2024)
- [Neural ranking models for document retrieval](https://mlsanity.com/paper/2102.11903/) (2021)
- [Optimizing Test-Time Query Representations for Dense Retrieval](https://mlsanity.com/paper/2205.12680/) (2022)
- [DREQ: Document Re-Ranking Using Entity-based Query Understanding](https://mlsanity.com/paper/2401.05939/) (2024)
- [Improved IR-based Bug Localization with Intelligent Relevance Feedback](https://mlsanity.com/paper/2501.10542/) (2025)
- [Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking](https://mlsanity.com/paper/2210.10695/) (2022)
- [PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer](https://mlsanity.com/paper/2101.07918/) (2021)
- [ReFIT: Relevance Feedback from a Reranker during Inference](https://mlsanity.com/paper/2305.11744/) (2023)
- [APRF-Net: Attentive Pseudo-Relevance Feedback Network for Query Categorization](https://mlsanity.com/paper/2104.11384/) (2021)
- [LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2204.11545/) (2022)
- [Retrieval Augmentation for T5 Re-ranker using External Sources](https://mlsanity.com/paper/2210.05145/) (2022)
- [Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders](https://mlsanity.com/paper/2405.03651/) (2024)
- [Online Distillation for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2306.09657/) (2023)
- [Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation](https://mlsanity.com/paper/2506.23662/) (2025)
- [REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking](https://mlsanity.com/paper/2510.11592/) (2025)
- [Graph-free Retrieval with Graph-Modified Embeddings](https://mlsanity.com/paper/2610.18410/) (2026)

## Abstract (arXiv)

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches. While neural retrieval models have recently demonstrated strong results for ad-hoc retrieval, combining them with PRF is not straightforward due to incompatibilities between existing PRF approaches and neural architectures. To bridge this gap, we propose an end-to-end neural PRF framework that can be used with existing neural IR models by embedding different neural models as building blocks. Extensive experiments on two standard test collections confirm the effectiveness of the proposed NPRF framework in improving the performance of two state-of-the-art neural IR models.