RAG / 检索增强生成

ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget

Riccardo Orlando, Pere-Lluis Huguet Cabot, Edoardo Barba, Roberto Navigli

机构 * Sapienza NLP Group, Sapienza University of Rome（罗马萨皮恩扎大学萨皮恩扎自然语言处理小组） 纠错

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

Comments Findings of the Association for Computational Linguistics ACL 2024

Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting

Gyanendra Shrestha, Chutain Jiang, Sai Akula, Vivek Yannam, Anna Pyayt, Michael Gubanov

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

Journal ref EDBT 2025, pp. 92-105

InsQABench: Benchmarking Chinese Insurance Domain Question Answering with Large Language Models

Jing Ding, Kai Feng, Binbin Lin, Jiarui Cai, Qiushi Wang, Yu Xie, Xiaojin Zhang, Zhongyu Wei, Wei Chen

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

SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis

Senbin Zhu, Chenyuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng

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

Comments This paper is to be published in the Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025)

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph

Yutong Zhang, Lixing Chen, Shenghong Li, Nan Cao, Yang Shi, Jiaxin Ding, Zhe Qu, Pan Zhou, Yang Bai

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

Comments Accepted by KDD 2025

CHESS: Contextual Harnessing for Efficient SQL Synthesis

Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang, Azalia Mirhoseini, Amin Saberi

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

Neon: News Entity-Interaction Extraction for Enhanced Question Answering

Sneha Singhania, Silviu Cucerzan, Allen Herring, Sujay Kumar Jauhar

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

Redefining Information Retrieval of Structured Database via Large Language Models

Mingzhu Wang, Yuzhe Zhang, Qihang Zhao, Junyi Yang, Hong Zhang

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

Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs

Lei Sun, Xinchen Wang, Youdi Li

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

Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction

Bowen Zhang, Harold Soh

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

Comments 18 pages, 3 figures, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Struct-X: Enhancing Large Language Models Reasoning with Structured Data

Xiaoyu Tan, Haoyu Wang, Xihe Qiu, Yuan Cheng, Yinghui Xu, Wei Chu, Yuan Qi

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

Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction

Yu-Hsiang Lin, Huang-Ting Shieh, Chih-Yu Liu, Kuang-Ting Lee, Hsiao-Cheng Chang, Jing-Lun Yang, Yu-Sheng Lin

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

KGValidator: A Framework for Automatic Validation of Knowledge Graph Construction

Jack Boylan, Shashank Mangla, Dominic Thorn, Demian Gholipour Ghalandari, Parsa Ghaffari, Chris Hokamp

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

Comments Text2KG 2024, ESWC 2024

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models

Ruotong Liao, Xu Jia, Yangzhe Li, Yunpu Ma, Volker Tresp

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

Comments 14 pages, Findings of NAACL 2024, Spotlight on TGL@NeurIPS2023

KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion

Yanbin Wei, Qiushi Huang, James T. Kwok, Yu Zhang

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

Comments Accepted to EMNLP 2023 Findings

Instructed Language Models with Retrievers Are Powerful Entity Linkers

Zilin Xiao, Ming Gong, Jie Wu, Xingyao Zhang, Linjun Shou, Jian Pei, Daxin Jiang

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

Comments Accepted to EMNLP 2023 Main

Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

Mattia Atzeni, Mikhail Plekhanov, Frédéric A. Dreyer, Nora Kassner, Simone Merello, Louis Martin, Nicola Cancedda

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

Comments Accepted at EMNLP 2023

Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation

Minki Kang, Jin Myung Kwak, Jinheon Baek, Sung Ju Hwang

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

Comments Preprint. Under review

BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis

Ayoub Harnoune, Maryem Rhanoui, Mounia Mikram, Siham Yousfi, Zineb Elkaimbillah, Bouchra El Asri

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

Analogical Inference Enhanced Knowledge Graph Embedding

Zhen Yao, Wen Zhang, Mingyang Chen, Yufeng Huang, Yi Yang, Huajun Chen

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

Comments Accepted by AAAI 2023

Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples

Linlin Liu, Xin Li, Ruidan He, Lidong Bing, Shafiq Joty, Luo Si

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

Comments Accepted by EMNLP 2022

DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking

Shen Huang, Yuchen Zhai, Xinwei Long, Yong Jiang, Xiaobin Wang, Yin Zhang, Pengjun Xie

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

Comments Accepted to NLPCC2022, 10 pages

ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science

ONOTE：面向专家级音乐智能的多模态记谱处理基准测试

Menghe Ma, Siqing Wei, Yuecheng Xing, Ziyue Zhu, Zhenghong Lin, Yaheng Wang, Fanhong Meng, Peijun Han, Luu Anh Tuan, Haoran Luo

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

AI总结 本文提出ONOTE基准测试，通过确定性流程消除记谱系统偏差，揭示多模态模型在感知准确性和音乐理论理解间的根本分歧。

Building An Integrated Vector Database System in PostgreSQL

在PostgreSQL中构建集成向量数据库系统

Jiayi Liu, Te Guo, Jianguo Wang

专题命中 图谱与结构化RAG ：vector search(abstract)；分类 cs.DB

AI总结 本文针对PostgreSQL-V 1.0的三个局限推出PostgreSQL-V 2.0，实现并发向量搜索更新、快速崩溃恢复与物理复制，吞吐量达前者36.4倍，恢复时间约20毫秒，是内嵌PostgreSQL的集成向量数据库系统。

Causal Episodic Memory for Feedback-Driven Agent Repair

用于反馈驱动智能体修复的因果情景记忆

Khang Nhat Hoang Vo, Tam Minh Chu, Anh Trac Duc Dinh, Thuyen Vinh Ha Bui, Tho Quan

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM（胡志明市理工大学计算机科学与工程学院（HCMUT，VNU-HCM）） 纠错

专题命中 图谱与结构化RAG ：retriever(abstract)；分类 cs.CL

AI总结 本文提出无需训练的MERIT智能体，通过维护双极性记忆辅助LLM智能体修复，在Spider、BIRD数据集上提升了Text-to-SQL任务的执行准确率，同时明确了因果跨查询记忆的适用场景。

TGMS: An Agent-Native Bi-Temporal Graph Management System

TGMS：一种原生代理双时态图管理系统

Xiaofei Zhang

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

AI总结 研究针对时态图问题中LLM代理常失败的情况，提出双时态属性图管理系统TGMS，将13个运算符作为代理工具，LLM规划调用，系统计算，能分离有效时间与事务时间，在基准测试中表现优异，开源代码等。

IDSTune: A Multi-Agent Collaborative Framework for Integrated Database System Tuning

IDSTune：一种用于集成数据库系统调优的多智能体协作框架

Yiyan Li, Guanli Liu, Renata Borovica-Gajic, Haoyang Li, Zihang Qiu, Xinmei Huang, Andreas Kipf, Cuiping Li, Hong Chen

专题命中 图谱与结构化RAG ：knowledge retrieval(abstract)；分类 cs.DB

AI总结 针对现有数据库调优方法未考虑组件相互依赖性及不足以处理多样工作负载等问题，提出IDSTune框架，通过大语言模型驱动多智能体协作联合优化多个配置组件，经实验验证其性能提升显著且调优速度快，适应性强。

Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes

基于LangGraph的基于图的智能体人工智能：长期运行的有状态业务流程的工作流路径

Daniel Pearson, Sidney Shapiro, Emiliano Sebastian Gonzalez Venegas, Sanad Al-Khatib, Aurora Pinzón Arzola

机构 * Dhillon School of Business, University of Lethbridge（莱斯布里奇大学迪隆商学院） ； Universidad de Guadalajara（瓜达拉哈拉大学） ； Al Hussein Technical University（侯赛因技术大学） ； Universidad de Guanajuato（瓜纳华托大学） 纠错

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

AI总结 本文为业务流程中的生成式AI系统提供基于图的工作流路径实践指南，提出三种可执行方法展示相关技术协同，按工作流复杂性定位LangGraph，解释其适用场景及实现模式，明确产品行为。

Comments 25 pages, 2 figures. With ancillary code

AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis

AnnoRetrieve：面向无结构文档分析的高效结构化检索

Teng Lin, Yuyu Luo, Nan Tang

专题命中 图谱与结构化RAG ：vector search(abstract)；分类 cs.IR

AI总结 本文提出AnnoRetrieve，通过结构化注释替代向量嵌入，实现高效精准的语义检索，降低LLM调用频率和成本，提升文档分析的准确性和可扩展性。

Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering

VL-KnG：从单目视频构建持久时空知识图谱以实现具身场景理解

Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov, Arthur Nigmatzyanov, Dmitrii Nalberskii, Sergey Zagoruyko, Gonzalo Ferrer

机构 * Applied AI Institute, Moscow, Russia（莫斯科应用人工智能研究所） 纠错

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

AI总结 VL-KnG通过构建时空知识图谱实现高效具身场景理解，采用LLM驱动的时空对象关联和图增强检索，无需3D重建，支持常数时间推理，优于现有前沿VLMs。