arXiv Computation and Language August 27, 2026 By Yuchao Wu, Junqin Li, Xingcheng Liang, Yongjie Chen, Yinghao Liang, Linyuan Mo, Guanxian Li

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

Read the original on arXiv Computation and Language →

SAG (SQL‑Retrieval Augmented Generation) is a structured retrieval framework that indexes documents as event‑entity pairs, forming latent hyperedges that preserve n‑ary relations without building a global knowledge graph. At query time, shared entities act as join keys, dynamically creating a query‑scoped neighborhood of related events while keeping each evidence chunk intact. Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue demonstrate that SAG outperforms existing dense‑retrieval baselines, achieving the highest recall and end‑to‑end QA performance, especially as reasoning‑chain complexity grows.

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 Computation and Language

Aug 25

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

arXiv:2608.12129v2 Announce Type: replace Abstract: While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementat...

By Yuchao Wu, Junqin Li, XingCheng Liang, Yongjie Chen, Yinghao Liang, Linyuan Mo, Guanxian Li

llms rag agents benchmarks data-engineering

arXiv AI

Jun 6

Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval

arXiv:2606. 05658v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge, but conventional pipelines rely on static, single-step retrieval that limits performance on complex queries.

By Anuj Maharjan, Devinder Kaur, Richard Molyet

llms rag agents benchmarks

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 9

UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough

arXiv:2603. 29875v3 Announce Type: replace-cross Abstract: One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector.

By Ryszard Tuora, Mateusz Gali\'nski, Micha{\l} Godziszewski, Micha{\l} Karpowicz, Mateusz Czy\.znikiewicz, Adam Kozakiewicz, Tomasz Zi\k{e}tkiewicz

llms rag benchmarks

arXiv AI

Jul 28

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

arXiv:2607. 22597v1 Announce Type: new Abstract: Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process.

By Hong-Yu An, Yun-Jian Zhang, Chen-Wei Liang, Tian-Yi Zhang, Jian Ding, Yi-Lun Wu, Ao-Bo Li, Wei-Cong Su, Saifullah, Mujiangshan Wang

llms rag nlp

arXiv AI

Jun 17

A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

arXiv:2606. 18075v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundamental limitation: entity-centric and chunk-centric approaches operate on representations anchored to original text without true knowledge fusion.

By Haoyang Zhong, Yifei Sun, Antong Zhang, Chunping Wang, Lei Chen, Yang Yang

llms rag nlp

One email a morning, machine-written

Related stories

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval

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

UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation