RAG / 检索增强生成

AugmenTest: Enhancing Tests with LLM-Driven Oracles

Shaker Mahmud Khandaker, Fitsum Kifetew, Davide Prandi, Angelo Susi

专题命中 长文档RAG ：RAG(abstract)

Comments Accepted for publication at 2025 IEEE Conference on Software Testing, Verification and Validation (ICST)

Preserving Culinary Traditions. A Crowdsourced Digital Collection of Cookbooks

Giulia Renda, Giulia Manganelli, Mila Fumini, Marilena Daquino

专题命中 长文档RAG ：RAG(abstract)

Comments 6 pages, 4 figures, "Me.Te. Digitali. Mediterraneo in rete tra testi e contesti", AIUCD2024

Journal ref Proceedings del XIII Convegno Annuale AIUCD2024, A cura di: Di Silvestro, Antonio ; Spampinato, Daria (2024). ISBN 978-88-942535-8-0

Superpixel-Based Building Damage Detection from Post-earthquake Imagery Using Deep Neural Networks

Jun Wang

专题命中 长文档RAG ：RAG(abstract)

DNAHLM -- DNA sequence and Human Language mixed large language Model

Wang Liang

专题命中 长文档RAG ：RAG(abstract)

Comments 18 pages, 7 figures

Checker Bug Detection and Repair in Deep Learning Libraries

Nima Shiri Harzevili, Mohammad Mahdi Mohajer, Jiho Shin, Moshi Wei, Gias Uddin, Jinqiu Yang, Junjie Wang, Song Wang, Zhen Ming, Jiang, Nachiappan Nagappan

专题命中 长文档RAG ：RAG(abstract)

Reusable Architecture Growth for Continual Stereo Matching

Chenghao Zhang, Gaofeng Meng, Bin Fan, Kun Tian, Zhaoxiang Zhang, Shiming Xiang, Chunhong Pan

专题命中 长文档RAG ：RAG(abstract)

Comments Extended version of CVPR 2022 paper "Continual Stereo Matching of Continuous Driving Scenes with Growing Architecture" - Accepted to TPAMI in 2024

Random Algebraic Graphs and Their Convergence to Erdos-Renyi

Kiril Bangachev, Guy Bresler

专题命中 长文档RAG ：RAG(abstract)

Comments Abstract shortened to match arXiv requirements

Structure Learning for Hybrid Bayesian Networks

Wanchuang Zhu, Ngoc Lan Chi Nguyen

专题命中 长文档RAG ：RAG(abstract)

Comments 28 pages, 5 figures, 6 tables

Safe Reinforcement Learning Using Robust Action Governor

Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

专题命中 长文档RAG ：RAG(abstract)

Reusing Static Analysis across Different Domain-Specific Languages using Reference Attribute Grammars

Johannes Mey, Thomas Kühn, René Schöne, Uwe Aßmann

专题命中 长文档RAG ：RAG(abstract)

Journal ref The Art, Science, and Engineering of Programming, 2020, Vol. 4, Issue 3, Article 15

Navigating the Cryptocurrency Landscape: An Islamic Perspective

Hina Binte Haq, Syed Taha Ali

专题命中 长文档RAG ：RAG(abstract)

Comments 6TH INTERNATIONAL CONFERENCE ON ISLAM AND LIBERTY

Minor complexities of finite operations

Slavcho Shtrakov

专题命中 长文档RAG ：RAG(abstract)

Comments 24 pages, 14 figures

Type and cotype with respect to arbitrary orthonormal systems

Stefan Geiss, Marius Junge

专题命中 长文档RAG ：RAG(abstract)

On Kinks and Bound States in the Gross-Neveu Model

Joshua Feinberg

专题命中 长文档RAG ：RAG(abstract)

Comments Revised version. A new section added with derivation of the DHN static configurations in the sector of broken supersymmetry. Some references added as well. 25 pp, latex, e-mail joshua@utaphy.ph.utexas.edu

Journal ref Phys. Rev. D 51, 4503 (1995)

On the complexity of finite valued functions

Sl. Shtrakov, I. Damyanov

专题命中 长文档RAG ：RAG(abstract)

Comments 23 pages, 4 figures, 6 tables, Preprint of the article is submitted for consideration in [WSPC (2015)] [http://www.worldscientific.com/worldscinet/ijfcs]

Dynamical Generation of Extended Objects in a $1+1$ Dimensional Chiral Field Theory: Non-Perturbative Dirac Operator Resolvent Analysis

J. Feinberg, A. Zee

专题命中 长文档RAG ：RAG(abstract)

Journal ref Phys.Rev.D56:5050-5065,1997

Flooding edge or node weighted graphs

Fernand Meyer

专题命中 长文档RAG ：RAG(abstract)

Comments 165 pages, 21 figures

Free Convex Algebraic Geometry

J. William Helton, Igor Klep, Scott McCullough

专题命中 长文档RAG ：RAG(abstract)

Comments 70 pages, survey

Journal ref In: "Semidefinite Optimization and Convex Algebraic Geometry" edited by G. Blekherman, P. Parrilo, R. Thomas, pp. 341-405, SIAM, 2013

A Universal Behavior of Half BPS Probes in the Superstar Ensemble

Ilies Messamah

专题命中 长文档RAG ：RAG(abstract)

Comments 34 pages + appendices

Journal ref JHEP12 (2012) 063

Semidefinite programming in matrix unknowns which are dimension free

J. William Helton, Igor Klep, Scott McCullough

专题命中 长文档RAG ：RAG(abstract)

Comments 25 pages; survey

Journal ref Pages 377-405 in the Handbook of Semidefinite, Conic and Polynomial Optimization edited by M. Anjos and J. B. Lasserre, Springer, 2012

HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs

HG-RAG：用于结构化知识图谱的层次引导检索增强生成

Pranav Yadav

机构 * University of California, Merced（加州大学默塞德分校） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(title)；retrieval augmented generation(abstract)；dense retrieval(abstract)

AI总结 研究针对RAG系统在处理结构化知识推理时的不足，提出HG-RAG框架，通过在层次知识图谱上遍历为语言模型提供结构化上下文，经多规模多类型查询评估，该框架在相关推理任务中优于基线，减少幻觉并保持一致性。

Comments 8 pages, 3 figures

mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA

mKG-RAG：利用多模态知识图谱在检索增强生成中进行知识密集型视觉问答

Xu Yuan, Liangbo Ning, Qingqing Ye, Wenqi Fan, Qing Li

机构 * The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(title,abstract)；retriever(abstract)；分类 cs.AI

AI总结 本文提出mKG-RAG框架，通过整合多模态知识图谱提升检索增强生成在知识密集型视觉问答中的性能，采用双阶段检索策略和图提取方法构建高质量知识图谱，实验表明优于现有方法。

Comments In Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'26), July 20-24, 2026, Melbourne, VIC, Australia

FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning

FT-RAG：一种面向复杂表格推理的细粒度检索增强生成框架

Zebin Guo, Weidong Geng, Ruichen Mao

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Zhejiang University（浙江大学） ； Zhejiang Lab（浙江实验室） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(title,abstract)；分类 cs.CL、cs.AI

AI总结 FT-RAG通过细粒度检索和多模态融合提升表格推理能力，引入多表RAG库增强训练数据，实现表格和单元格命中率显著提升。

Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents

结构感知检索增强生成：面向对话代理的噪声数据结构化检索增强生成

Kaiqiao Han, LuAn Tang, Renliang Sun, Peng Yuan, Wei Cheng, Haoyu Wang, Wei Wang, Yizhou Sun, Haifeng Chen

机构 * UCLA（加州大学洛杉矶分校） ； NEC Labs（日本电装实验室） 纠错

专题命中 图谱与结构化RAG ：RAG(title,summary_cn)；retrieval augmented generation(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 提出结构感知检索增强生成（SA-RAG），通过表格作为中间结构化表示来减少噪声并保留关键信息，结合质量感知的表格元数据生成框架和优化方法，在噪声真实数据集上显著优于现有RAG基线。

AkasicDB: Demonstrating Omni RAG with a Unified Vector-Graph-Relational DBMS

AkasicDB：展示基于统一向量-图-关系型数据库管理系统的全模态检索增强生成（Omni RAG）

Geonho Lee, Jeongho Park, Donghyoung Han, Min-Soo Kim

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(abstract)；vector search(abstract)；分类 cs.AI、cs.DB

AI总结 AkasicDB是一款支持在单一框架内协同执行向量、图、关系操作的数据库系统，可实现全模态检索增强生成（Omni RAG），演示显示其性能优于仅向量方法，且暴露了现有数据库架构的局限。

Comments SIGMOD 2026 demonstration

Journal ref SIGMOD Companion 2026, pp. 70-73

MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

MKG-RAG-Bench：多模态知识图谱增强生成中的检索基准

Xiaochen Wang, Bao Hoang, Han Liu, Ting Wang, Fenglong Ma

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； Michigan State University（密歇根州立大学） ； Dalian University of Technology（大连理工大学） ； Stony Brook University（石溪大学） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.AI

AI总结 提出MKG-RAG-Bench基准，通过构建跨领域多模态知识图谱和问答数据集，系统评估多模态知识图谱增强生成中的检索性能，揭示检索质量对生成结果的决定性作用。

Comments Accepted by KDD'26

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

LlamaRec-LKG-RAG：一种用于基于大语言模型的排序的单遍可学习知识图谱-RAG框架

Vahid Azizi, Fatemeh Koochaki

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结 该研究提出LlamaRec-LKG-RAG框架，将个性化知识图谱上下文集成到LLM推荐排序中，经ML-100K等数据集实验，在MRR等指标上较LlamaRec取得提升，为知识感知个性化推荐奠定基础。

RAG over Thinking Traces Can Improve Reasoning Tasks

RAG 基于思考轨迹可提升推理任务

Negar Arabzadeh, Wenjie Ma, Sewon Min, Matei Zaharia

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结 提出检索思考轨迹而非文档，通过 T3 方法将其转化为结构化表示，在推理任务上显著提升性能，超越标准 RAG 和无 RAG 基线。

An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach

基于本体的法律规范图式RAG：一种结构、时间与确定性方法

Hudson de Martim

机构 * Federal Senate of Brazil（巴西联邦议会） 纠错

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retrieval-augmented generation(abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结 本文提出一种基于本体的图式RAG框架，通过建模法律规范的结构和时间特性，解决法律领域检索增强生成系统中对法律层级、时间性和因果关系的忽视问题。

Comments Major revision for clarity and academic precision. Updated title and abstract. Refined core terminology, contributions, related work, and shifted the implementation to a conceptual architecture. Added new arguments to strengthen the paper's thesis

Journal ref Legal Knowledge and Information Systems (JURIX 2025), Frontiers in Artificial Intelligence and Applications, IOS Press, 2025

GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

FastInsight: 图形RAG中通过融合运算实现快速且有洞察力的检索

Seonho An, Chaejeong Hyun, Min-Soo Kim

专题命中 图谱与结构化RAG ：RAG(title,title_cn)；retriever(abstract)；分类 cs.IR、cs.AI

AI总结 FastInsight通过融合运算提升图RAG检索效率和洞察力，改进检索准确性和生成质量。

Comments CIKM 2026