arXiv Machine Learning August 4, 2026 By Ant\'onio Pereira Barata

Do Static Embeddings Add Value to Hybrid Dutch Retrieval?

Read the original on arXiv Machine Learning →

arXiv:2608. 02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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 Machine Learning

Jul 9

MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese

arXiv:2607. 04581v2 Announce Type: replace-cross Abstract: Text embeddings for Portuguese have no dedicated benchmark: evaluation rests on translated corpora such as English MS MARCO or on thin multilingual coverage, with native tasks scattered and unconsolidated.

By Tardelli Ronan Coelho Stekel

rag benchmarks

arXiv Machine Learning

Jul 7

MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese

arXiv:2607. 04581v1 Announce Type: cross Abstract: Text embeddings for Portuguese have no dedicated benchmark: evaluation rests on translated corpora such as English MS MARCO or on thin multilingual coverage, with native tasks scattered and unconsolidated.

By Tardelli Ronan Coelho Stekel

rag benchmarks

arXiv AI

Jul 16

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

arXiv:2602. 09616v2 Announce Type: replace-cross Abstract: Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information.

By Zeinab Sadat Taghavi, Ali Modarressi, Hinrich Schutze, Andreas Marfurt

rag

arXiv Machine Learning

Jun 15

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

arXiv:2604. 23336v3 Announce Type: replace-cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs.

By Teng Chen, Sheng Xu, Feixiang Guo, Xiaoyu Wang, Qingqing Gu, Hongyan Li, Luo Ji

llms rag robotics efficiency benchmarks

arXiv AI

Jun 24

MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval

arXiv:2606. 24200v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) in clinical settings increasingly requires multilingual retrieval against predominantly English evidence corpora.

By Junhyeok Lee, Han Jang, Hyeonjin Goh, Kyu Sung Choi

rag benchmarks safety

Related stories

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

MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese

MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval