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

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

3d ago

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

arXiv Computation and Language

2d ago

ConvergeWriter: Data-Driven Bottom-Up Article Construction

ConvergeWriter introduces a bottom‑up, data‑driven framework for long‑form document generation that first retrieves exhaustive knowledge from a source corpus and clusters it into distinct knowledge groups. These clusters then guide the creation of a hierarchical outline and the final text, ensuring the output is strictly grounded in the retrieved material and traceable to its sources. Experiments on 14B and 32B LLMs show that this approach matches or surpasses state‑of‑the‑art baselines, especially in scenarios requiring high factual fidelity and structural coherence.

By Binquan Ji, Jiaqi Wang, Ruiting Li, Xingchen Han, Yiyang Qi, Shichao Wang, Yifei Lu, Yuantao Han, Feiliang Ren

llms rag benchmarks safety

One email a morning, machine-written

Related stories

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

ConvergeWriter: Data-Driven Bottom-Up Article Construction