Hugging Face Trending Papers July 21, 2026

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

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

benchmarks

arXiv AI

Jun 30

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

arXiv:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.

By Sadanand Singh, Allam Reddy, Manan Chopra

rag nlp benchmarks

arXiv AI

Jul 22

M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation

arXiv:2603. 26667v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) turns external documents into evidence for large language models.

By Xu Sun, Tongkai Xu, Baiheng Xie, Li Huang, Qiang Gao, Kunpeng Zhang

llms rag

arXiv Machine Learning

Aug 4

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

arXiv:2608. 00065v1 Announce Type: cross Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts.

By Shusen Zhang, Junyi Hu, Ye Feng, Ziteng Wang, Zhaoyuan Pan, Guosheng Dong, Xiaojun Yuan, Jiangshou Hong, Xiangzhi Wang

rag nlp

arXiv AI

Jun 4

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

arXiv:2605. 30120v3 Announce Type: replace-cross Abstract: Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions.

By Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng, Stefanie Jegelka, Chenyu You

rag efficiency benchmarks

arXiv Machine Learning

Jul 31

OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval

arXiv:2607. 27475v1 Announce Type: cross Abstract: In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to refined ranking.

By Ziwei Li, Shuyao Li, Xufeng Cai, Xue Zou, Yiming Ma, Huiting Lu, Wujie Yan, Zhichen Zhao, Yang Lu, Zhe Wang, Rui Luo, Zhengyu Su, Dan Zhang, Ji Liu

safety

arXiv AI

Jun 4

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples

arXiv:2606. 04646v1 Announce Type: cross Abstract: Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text.

By Mengao Zhang, Xiang Yang, Chang Liu, Tianhui Tan, Ke-wei Huang

llms rag nlp benchmarks data-engineering

Related stories

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples