RAG / 检索增强生成

Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications

具有知识图谱的代理RAG用于现实世界应用中的复杂多跳推理

Jean Lelong, Adnane Errazine, Annabelle Blangero

机构 * Ekimetrics 纠错

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

AI总结 INRAExplorer通过多工具架构和知识图谱实现复杂多跳推理，提升专业领域知识交互能力。

Comments ECAI 2025 demo track, 4 pages

Journal ref ECAI 2025, Frontiers in Artificial Intelligence and Applications, vol. 413, pp. 5163-5166, IOS Press

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

PIDP-Attack：将提示注入与数据库污染攻击结合在检索增强生成系统中

Haozhen Wang, Haoyue Liu, Jionghao Zhu, Zhichao Wang, Yongxin Guo, Xiaoying Tang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Taobao and Tmall Group（淘宝和天猫集团） 纠错

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

AI总结 本文提出PIDP-Attack，结合提示注入与数据库污染攻击，针对检索增强生成系统中的对抗攻击问题，通过在推理时添加恶意字符并注入少量污染文档，有效操控LLM响应，实验显示其在开放域问答任务中攻击成功率提升4%-16%。

CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

CodeRefine: 一种提升研究论文中大语言模型生成代码实现的管道

Ekaterina Trofimova, Emil Sataev, Abhijit Singh Jowhari

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

AI总结 CodeRefine通过多步骤方法将论文方法转化为功能代码，利用预定义本体构建知识图谱，并通过回顾性检索增强生成方法提升代码准确性，有效解决理论研究与实践实现之间的桥梁问题。

Comments The results mentioned in the paper are non-reproducible. We have rechecked the metrics, and they do not match with the ones that have been provided in the paper. Therefore, we accept that this article is neither suitable nor up to the mark for the scientific community and must be with-drawn. We fully understand the consequences, and would like to wishfully retract this article