arXiv Computation and Language August 25, 2026 By Hridya Dhulipala, Rajesh Ombase, Michael Wang, Tien N. Nguyen

W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases

Read the original on arXiv Computation and Language →

W-RAG is a source-aware retrieval framework designed for enterprise document generation from heterogeneous knowledge bases. It uses ontology-guided retrieval, local ranking within each knowledge base, and source-level weighting to balance evidence from diverse sources. A new dataset covering multiple document types and industry domains demonstrates that W-RAG improves document coverage and generation quality compared to standard RAG pipelines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Sep 16

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

The paper introduces ORDER, a task‑conditioned retrieval‑augmented generation framework that dynamically adapts both indexing and retrieval strategies to each incoming query. It first clusters questions to learn cluster‑specific chunking, metadata filtering, and reranking settings, then routes queries to the appropriate pre‑built index via nearest‑centroid assignment. Additionally, a supervised query router predicts relevant collections and a Uniform Multi‑source Sampler distributes the retrieval budget evenly across selected sources, yielding superior performance on heterogeneous historical archives compared to existing RAG systems.

By Aur\'elien Pellet (LRE), Julien Perez, Marie Puren

rag 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 AI

Aug 24

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

arXiv:2608.21252v1 Announce Type: cross Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationshi...

By Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh, Jiawei Han

llms rag nlp

arXiv AI

Jun 12

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

arXiv:2606. 13550v1 Announce Type: new Abstract: Retrieval augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence.

By Hoin Jung, Xiaoqian Wang

rag nlp benchmarks

arXiv AI

Jul 2

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

arXiv:2607. 00013v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al.

By Asit Desai, Aman Kumar, Prashant Devadiga

llms rag nlp

arXiv AI

Jul 28

Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach

arXiv:2607. 22584v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility.

By Yuktha Tata Koganti, Hugo Garrido-Lestache Belinchon

rag safety

One email a morning, machine-written

Related stories

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

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

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach