arXiv AI August 25, 2026 By Jing Liu, Yongxing Qi, Muchen Jiang, Chengnan Hu, Qingqing Peng, Haoming Wang, Yuqing Wang, Yang Yu, Xu Zhang, Ting Wu

From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv AI

Jun 11

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.

By Yuqi Zhang, Di Zhang

llms rag benchmarks safety

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 AI

Jun 3

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

arXiv:2606. 02814v1 Announce Type: cross Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs.

By Francisco Valentini, Edgar Altszyler, Martin Fajcik

llms rag benchmarks safety

arXiv AI

Aug 13

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.

By Zhipeng Song, Yizhi Zhou, Xiangyu Kong, Jiulong Jiao, Xuezhou Ye, Chunqi Gao, Xueqing Shi, Yu Wang, Yuhang Zhou, Heng Qi

llms 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 16

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking

arXiv:2606. 15998v1 Announce Type: cross Abstract: Entity-aware document retrieval uses query-associated entities as ranking signals, assuming that semantically relevant entities are also useful retrieval signals.

By Utshab Kumar Ghosh, Shubham Chatterjee

efficiency

One email a morning, machine-written

Related stories

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

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

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

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

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking