arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

RAG / 检索增强生成

检索增强生成、向量检索、知识库问答和面向大模型的搜索系统。

共收录 962 信号源:cs.IR, cs.CL, cs.AI, cs.DB

1. 图谱与结构化RAG 962 篇

2506.09247 2025-06-12 cs.LG 82%

Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation

Karl Löwenmark, Daniel Strömbergsson, Chang Liu, Marcus Liwicki, Fredrik Sandin

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00888 2025-06-03 cs.SE 82%

An Integrated Platform for LEED Certification Automation Using Computer Vision and LLM-RAG

Jooyeol Lee

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10951 2025-05-20 cs.LG 82%

SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache

Qiuyu Zhu, Liang Zhang, Qianxiong Xu, Cheng Long, Jie Zhang

机构 * Nanyang Technological University(南洋理工大学) Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11838 2025-04-17 cs.CV 82%

A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification

Bianca Lamm, Janis Keuper

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.20299 2025-02-17 cs.DC 82%

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

Jiaxing Li, Chi Xu, Lianchen Jia, Feng Wang, Cong Zhang, Jiangchuan Liu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.13121 2024-06-21 cs.CL cs.AI cs.IR 82%

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Sébastien M. R. Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu

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

Comments 29 pages. Dataset available at https://github.com/google-deepmind/loft

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.29778 2026-06-30 cs.DB cs.AI cs.CL cs.IR 81%

Mandol: An Agglomerative Agent Memory System for Long-Term Conversations

Mandol:一种用于长期对话的聚合式智能体记忆系统

Yuhan Zhang, Zhiyuan Guo, Ziheng Zeng, Wei Wang, Wentao Wu, Lijie Xu

机构 * Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所) Microsoft Research(微软研究院)

专题命中 图谱与结构化RAG :RAG(abstract,abstract_cn);hybrid retrieval(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 提出Mandol聚合式记忆系统,通过统一内存原生架构整合碎片化记忆,结合层次化记忆模型、聚合语义数据结构与量化查询机制,在长期对话基准上取得最佳准确率并实现5.4倍检索加速。

Comments 10 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.01385 2026-06-02 cs.SE cs.AI 81%

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

桥接需求与架构:基于外部知识和分层记忆的多智能体编排

Ruiyin Li, Yiran Zhang, Xiyu Zhou, Yangxiao Cai, Peng Liang, Weisong Sun, Jifeng Xuan, Zhi Jin, Yang Liu

机构 * School of Computer Science, Wuhan University(武汉大学计算机学院) Nanyang Technological University(南洋理工大学)

专题命中 图谱与结构化RAG :RAG(summary_cn,abstract);分类 cs.AI

AI总结 提出MAAD框架,通过编排四个专业智能体(分析师、建模师、设计师、评估师),结合RAG注入架构标准与分层记忆机制,自动将需求规格转化为多视图架构蓝图并评估质量属性。

Comments 39 pages, 7 images, 5 tables, Manuscript submitted to a Journal (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.00050 2026-06-02 cs.AI cs.CL cs.DB cs.IR 81%

Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs

Grokers: 基于类型化知识图谱的自底向上归纳理解与写入时智能

Gregory Magarshak

机构 * Gregory Magarshak

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

AI总结 提出Grokers架构,通过自底向上的依赖子图归纳遍历构建持久结构化理解,将智能推至写入时,实现零额外LM成本的查询,并证明字节同一性、累积单调性和双遍历顺序三个形式性质。

Comments 6 pages; second in a series with the Magarshak Machine / SPACER paper and the Context paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.27331 2026-05-27 cs.AI 81%

Maat: The Agentic Legal Research Assistant for Competition Protection

Maat: 面向竞争保护的法律研究智能助手

Basant Mounir, Farida Madkour, Amira Abdelaziz, Asmaa Sami

机构 * Cairo Egypt(开罗埃及)

专题命中 图谱与结构化RAG :RAG(summary_cn,abstract);分类 cs.AI

AI总结 提出Maat,一种基于ReAct框架的智能法律研究助手,通过RAG、网络搜索和用户澄清机制,在竞争法案例检索中显著优于现有通用和专用法律助手。

Comments 5 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23459 2026-05-25 cs.SE cs.AI 81%

AI Assurance: A Comprehensive Testing Strategy for Enterprise AI Systems

AI 保证:企业 AI 系统的综合测试策略

Chitra Badagi, Divye Singh, Animesh Sen, Adinath Shirsath

机构 * Thoughtworks Technologies(Thoughtworks技术公司)

专题命中 图谱与结构化RAG :RAG(summary_cn,abstract);分类 cs.AI

AI总结 本文针对基于大语言模型、检索管道和自主代理的企业 AI 系统,提出了一种以持续风险降低为核心、将评估作为核心工程学科、并关注组织影响的综合保证策略,包括结构化的 AI 故障分类法、五层 AI 保证金字塔以及评估驱动开发、RAG 系统测试、模型生命周期管理和治理的操作指南。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12301 2026-04-15 cs.DC cs.AI cs.SE 81%

Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads

Local-Splitter:七种减少云LLM令牌使用量策略的测量研究

Justice Owusu Agyemang, Jerry John Kponyo, Elliot Amponsah, Godfred Manu Addo Boakye, Kwame Opuni-Boachie Obour Agyekum

机构 * Sperix Labs(Sperix实验室) VIA Cybersecurity Lab, KNUST(VIA网络安全实验室,科罗尼斯特大学) Quantum and Assistive Technologies Lab, KNUST(量子与辅助技术实验室,科罗尼斯特大学)

专题命中 图谱与结构化RAG :RAG(summary_cn,abstract);分类 cs.AI

AI总结 本文研究了七种减少云LLM令牌使用量的策略,通过测量发现本地路由与提示压缩组合在编辑密集型任务中可节省45-79%的云令牌,而RAG密集型任务中完整策略集可节省51%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16700 2025-11-24 cs.DB cs.AI 81%

RAG-Driven Data Quality Governance for Enterprise ERP Systems

面向企业ERP系统的RAG驱动数据质量治理

Sedat Bin Vedat, Enes Kutay Yarkan, Meftun Akarsu, Recep Kaan Karaman, Arda Sar, Çağrı Çelikbilek, Savaş Saygılı

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

AI总结 本文提出一种基于RAG的数据质量治理方法,通过自动化清洗与LLM生成SQL查询,提升企业ERP系统中多语言数据处理效率与准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23495 2025-11-05 cs.CL cs.AI cs.LG 81%

Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking

Liangliang Zhang, Zhuorui Jiang, Hongliang Chi, Haoyang Chen, Mohammed Elkoumy, Fali Wang, Qiong Wu, Zhengyi Zhou, Shirui Pan, Suhang Wang, Yao Ma

机构 * Rensselaer Polytechnic Institute(罗切斯特理工学院) University of Toronto(多伦多大学) Pennsylvania State University(宾夕法尼亚州立大学) AT&T Chief Data Office(AT&T首席数据办公室) Griffith University(格里菲斯大学)

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

Comments Accepted at NeurIPS 2025 Datasets and Benchmarks Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08958 2025-10-13 cs.AI cs.IR 81%

EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory

Zirui Liao

机构 * Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00842 2025-07-28 cs.CL cs.AI 81%

Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience

Jiawei Gu, Ziting Xian, Yuanzhen Xie, Ye Liu, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li

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

Comments ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.00982 2025-06-03 cs.CL cs.AI 81%

Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice

Federico Ravenda, Seyed Ali Bahrainian, Andrea Raballo, Antonietta Mira, Noriko Kando

机构 * Euler Institute, Università della Svizzera italiana(欧拉研究所,瑞士大学) National Institute of Informatics(国家信息研究所) Brown University(布朗大学) University of Tübingen(图宾根大学) Insubria University(因斯布里亚大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11108 2025-02-18 cs.CL cs.AI 81%

Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications

Alexandru Lecu, Adrian Groza, Lezan Hawizy

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14057 2024-10-21 cs.CL cs.AI 81%

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Saloni Potdar, Yunyao Li

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

Comments Accepted at EMNLP 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.14745 2024-06-25 cs.CL cs.AI 81%

Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks

Sefika Efeoglu, Adrian Paschke

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

Comments preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.15436 2024-05-27 cs.IR cs.AI 81%

Hybrid Context Retrieval Augmented Generation Pipeline: LLM-Augmented Knowledge Graphs and Vector Database for Accreditation Reporting Assistance

Candace Edwards

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

Comments 17 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.15776 2023-10-26 cs.CL cs.AI 81%

Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation

Micheal Abaho, Yousef H. Alfaifi

专题命中 图谱与结构化RAG :dense retrieval(title);retriever(abstract);分类 cs.CL、cs.AI

Comments Article has already been puclished to Journal of Artificial Intelligence Research (JAIR)

Journal ref Journal of Artificial Intelligence Research, 78, 2023, 269-285

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.27748 2026-07-31 cs.IR cs.AI cs.DB 新提交 80%

A Structured Knowledge Infrastructure for Domain-Specific Data Asset Discovery

面向领域特定数据资产发现的结构化知识基础设施

Mengdi Chen, Yuanxin Huang, Yulin Jiang, Wei Sun

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

AI总结 针对企业数据分析智能体检索数据资产的失效问题,提出两层解决方案,经小红书广告数据仓库验证,可大幅提升检索准确率与知识覆盖率,降低延迟。

Comments 6 pages, 2 figures, 2 tables. Submitted to DAI 2026 Industry Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20135 2026-06-18 cs.CL cs.AI cs.IR 80%

KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration

KNIGHT: 基于知识图谱的多选题生成与自适应难度校准

Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari, Mahdi Noori, Farhan Farsi, Behnam Bahrak

机构 * University of Tehran(塔里班大学) Independent Researcher(独立研究员) Amirkabir University of Technology(阿米尔卡比尔技术大学) TEIAS Institute(TEIAS研究所)

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

AI总结 KNIGHT通过构建领域特定知识图谱,实现高效生成多选题数据集,支持自适应难度控制,提升生成效率与质量,验证了其在多个领域内的有效性。

Comments Accepted at the Third Conference on Parsimony and Learning (CPAL 2026). 36 pages, 12 figures. (Equal contribution: Yasaman Amou Jafari and Mahdi Noori.)

Journal ref Conference on Parsimony and Learning, Proceedings of Machine Learning Research, 328:989-1024, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30966 2026-06-01 cs.IR cs.AI cs.CL 80%

Reading Between the Citations: A Typed Claim Network for Scientific Literature

解读引用:面向科学文献的类型化主张网络

Ning Ding, Sergio J. Rodríguez Méndez, Pouya G. Omran

机构 * Australian National University(澳大利亚国立大学)

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

AI总结 针对现有知识图谱忽略引用立场的问题,提出将文献间引用具体化为带有立场标签的类型化主张网络,并构建了包含8260条主张的实例,在检索增强、立场摘要和拓扑分析三个任务上验证其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14665 2026-05-18 cs.AI cs.CL cs.IR 80%

Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI

Falkor-IRAC:用于印度司法AI的图约束生成:在验证法律推理中的应用

Joy Bose

机构 * Independent Researcher(独立研究者)

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

AI总结 本文提出Falkor-IRAC框架,通过图约束生成解决印度法律AI中的验证法律推理问题,利用IRAC知识图谱进行结构化推理,并通过验证代理检查生成路径的正确性。

Comments 20 pages, 8 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06002 2026-04-30 cs.AI cs.CL cs.IR 80%

Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs

确定性法律代理:用于可审计时间知识图谱推理的规范性原始API

Hudson de Martim

机构 * Federal Senate of Brazil(巴西联邦议会)

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

AI总结 本文提出SAT-Graph API,通过确定性符号子系统与概率语言模型交互,实现法律领域可审计的时间知识图谱推理,将单次检索生成改为主动推理-行动-观察流程。

Comments Substantially revised version consolidating the paper as a formal SAT-Graph API specification: clarifies Probability Isolation and post-anchoring determinism, broadens semantic anchoring to open and thematic legal queries, refines the data models and temporal primitives, and strengthens the use cases, limitations, and bibliography

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23588 2026-04-28 cs.AI cs.CL cs.IR 80%

FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification

FinGround:通过原子性声明验证检测和支撑金融幻觉

Dongxin Guo, Jikun Wu, Siu Ming Yiu

机构 * The University of Hong Kong(香港大学) Stellaris AI Limited(Stellaris AI有限公司)

专题命中 图谱与结构化RAG :RAG(abstract,abstract_cn);hybrid retrieval(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 FinGround通过三阶段验证-支撑流程,针对金融文档问答中的计算错误进行验证和修正,有效降低幻觉率,其在金融领域具有重要应用价值。

Comments Accepted to ACL 2026 Industry Track. 14 pages, 1 figure, 14 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.22758 2026-04-28 cs.IR cs.AI cs.CL 80%

RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching

RedParrot:通过查询语义缓存加速业务分析中的自然语言到DSL转换

Tong Wang, Yongqin Xu, Jianfeng Zhang, Lingxi Cui, Wenqing Wei, Suzhou Chen, Huan Li, Ke Chen, Lidan Shou

机构 * State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室)

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

AI总结 RedParrot通过语义缓存加速自然语言到领域特定语言的转换,提升业务分析效率与准确性,实验显示在六个真实企业数据集上平均提速3.6倍,准确率提升8.26%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05569 2026-04-21 cs.IR cs.AI cs.CL 80%

CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain

CBR-to-SQL:重新思考基于检索的文本到SQL方法:在医疗领域使用基于案例的推理

Hung Nguyen, Hans Moen, Pekka Marttinen

机构 * Department of Computer Science Aalto University(奥卢大学计算机科学系) Department of Clinical Medicine Aalborg University(奥尔堡大学临床医学系)

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

AI总结 本文提出CBR-to-SQL框架,通过分解检索增强生成的两阶段检索,提升医疗领域文本到SQL的准确性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏