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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hang, Wang, Xiao, Koopman, Bevan, Zuccon, Guido
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
by: Li, Hang, et al.
Published: (2025)

TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval
by: Li, Hang, et al.
Published: (2024)

Dense Retrieval with Continuous Explicit Feedback for Systematic Review Screening Prioritisation
by: Mao, Xinyu, et al.
Published: (2024)

Team IELAB at TREC Clinical Trial Track 2023: Enhancing Clinical Trial Retrieval with Neural Rankers and Large Language Models
by: Zhuang, Shengyao, et al.
Published: (2024)

PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
by: Zhuang, Shengyao, et al.
Published: (2024)

Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems
by: Zhuang, Shengyao, et al.
Published: (2024)

Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
by: Zhou, Yongjie, et al.
Published: (2026)

Does Vec2Text Pose a New Corpus Poisoning Threat?
by: Zhuang, Shengyao, et al.
Published: (2024)

A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR
by: Mao, Xinyu, et al.
Published: (2024)

2D Matryoshka Training for Information Retrieval
by: Wang, Shuai, et al.
Published: (2024)

Reassessing Large Language Model Boolean Query Generation for Systematic Reviews
by: Wang, Shuai, et al.
Published: (2025)

Whole-Pool Setwise Reranking with Long-Context Language Models
by: Li, Hang, et al.
Published: (2026)

ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search
by: Wang, Shuai, et al.
Published: (2024)

A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
by: Zhuang, Shengyao, et al.
Published: (2023)

AutoBool: An Reinforcement-Learning trained LLM for Effective Automated Boolean Query Generation for Systematic Reviews
by: Wang, Shuai, et al.
Published: (2025)

Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
by: Schlatt, Ferdinand, et al.
Published: (2024)

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
by: Yin, Yu, et al.
Published: (2026)

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
by: Zhuang, Shengyao, et al.
Published: (2025)

VISA: Retrieval Augmented Generation with Visual Source Attribution
by: Ma, Xueguang, et al.
Published: (2024)

Starbucks-v2: Improved Training for 2D Matryoshka Embeddings
by: Zhuang, Shengyao, et al.
Published: (2024)

Zero-shot Generative Large Language Models for Systematic Review Screening Automation
by: Wang, Shuai, et al.
Published: (2024)

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
by: Zhuang, Shengyao, et al.
Published: (2025)

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback
by: Jedidi, Nour, et al.
Published: (2024)

Unlearning for Federated Online Learning to Rank: A Reproducibility Study
by: Tao, Yiling, et al.
Published: (2025)

How to Forget Clients in Federated Online Learning to Rank?
by: Wang, Shuyi, et al.
Published: (2024)

Leveraging LLMs for Unsupervised Dense Retriever Ranking
by: Khramtsova, Ekaterina, et al.
Published: (2024)

DenseReviewer: A Screening Prioritisation Tool for Systematic Review based on Dense Retrieval
by: Mao, Xinyu, et al.
Published: (2025)

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
by: Wang, Zihao, et al.
Published: (2026)

On the impact of retrieved content representations in RAG Pipelines
by: Ross, Jonathan J, et al.
Published: (2026)

Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition
by: Yao, Zheng, et al.
Published: (2025)

Embark on DenseQuest: A System for Selecting the Best Dense Retriever for a Custom Collection
by: Khramtsova, Ekaterina, et al.
Published: (2024)

When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment
by: Yu, Chuting, et al.
Published: (2026)

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
by: Tsirigotis, Christos, et al.
Published: (2025)

Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
by: Li, Minghan, et al.
Published: (2024)

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
by: Park, Seongwan, et al.
Published: (2025)

Towards Dynamic Dense Retrieval with Routing Strategy
by: Su, Zhan, et al.
Published: (2026)

Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval
by: Xi, Jiaqi, et al.
Published: (2026)

Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
by: Cao, Jiawei, et al.
Published: (2025)

Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering
by: Chen, Haodong, et al.
Published: (2025)

Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
by: Schlatt, Ferdinand, et al.
Published: (2024)