RAG / 检索增强生成

Climate Finance Bench

Rafik Mankour, Yassine Chafai, Hamada Saleh, Ghassen Ben Hassine, Thibaud Barreau, Peter Tankov

机构 * Institut Louis Bachelier（路易·巴舍利尔研究所） ； CREST, ENSAE, Institut Polytechnique de Paris（CREST、ENSAE、巴黎理工学院） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL

Comments Dataset is available at https://github.com/Pladifes/climate_finance_bench

Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models

Zhengliang Shi, Lingyong Yan, Weiwei Sun, Yue Feng, Pengjie Ren, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Zhaochun Ren

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR

A Multi-Granularity Retrieval Framework for Visually-Rich Documents

Mingjun Xu, Zehui Wang, Hengxing Cai, Renxin Zhong

机构 * DP Technology（DP技术） ； School of Intelligent Systems Engineering, Sun Yat-Sen University, Shenzhen, China（中山大学智能系统工程学院，深圳，中国） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；hybrid retrieval(abstract)；分类 cs.IR

SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration

Qiang Sun, Tingting Bi, Sirui Li, Eun-Jung Holden, Paul Duuring, Kai Niu, Wei Liu

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR

ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization

Yunxiao Shi, Xing Zi, Zijing Shi, Haimin Zhang, Qiang Wu, Min Xu

机构 * University of Technology Sydney（悉尼技术大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.CL

Comments Draft Paper

Journal ref Frontiers in Artificial Intelligence and Applications, Vol. 392 (ECAI 2024), pp. (2024)

Agentic Verification for Ambiguous Query Disambiguation

Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, Yuxiong He

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL

Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid

Yunfeng Li, Jiqun Zhang, Guofu Liao, Xue Shi, Junhong Liu

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；dense retrieval(abstract)；分类 cs.CL

Comments 12 pages, 10 figures

Inference Scaling for Bridging Retrieval and Augmented Generation

Youngwon Lee, Seung-won Hwang, Daniel Campos, Filip Graliński, Zhewei Yao, Yuxiong He

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL

SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer

Anmol Gautam, Kishore Kumar, Adarsh Jha, Mukunda NS, Ishaan Bhola

专题命中 检索器与排序 ：retrieval augmented generation(abstract)；retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao, Shafiq Joty, Lidong Bing

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.CL

Comments Work in progress

LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ

Marc-Antoine Allard, Matin Ansaripour, Maria Yuffa, Paul Teiletche

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.AI

Vietnamese Legal Information Retrieval in Question-Answering System

Thiem Nguyen Ba, Vinh Doan The, Tung Pham Quang, Toan Tran Van

专题命中 检索器与排序 ：retrieval augmented generation(abstract)；RAG(abstract)；vector search(abstract)；分类 cs.IR

Comments 7 pages

Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval

Zizhong Li, Haopeng Zhang, Jiawei Zhang

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR

Comments 13 pages, 7 figures, 3 tables

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Pengyuan Zhou

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL

Comments Accepted to ACL'24 (Findings)

COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

Kush Juvekar, Anupam Purwar

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；hybrid retrieval(abstract)；分类 cs.IR

GAIA: A General AI Assistant for Intelligent Accelerator Operations

Frank Mayet

专题命中 检索器与排序 ：retrieval augmented generation(abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.CL

Retrieval-Augmented Audio Deepfake Detection

Zuheng Kang, Yayun He, Botao Zhao, Xiaoyang Qu, Junqing Peng, Jing Xiao, Jianzong Wang

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.AI

Comments Accepted by the 2024 International Conference on Multimedia Retrieval (ICMR 2024)

Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check

Linhao Ye, Zhikai Lei, Jianghao Yin, Qin Chen, Jie Zhou, Liang He

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.AI

Bridging the Preference Gap between Retrievers and LLMs

Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL

SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads

SMART：用于动态产品广告的大语言模型增强混合检索

Congfei Zhang, Jingxiao Ma, Xiaodong Liu, Hsiang-wei Chao, Siman Wang, Ge Liu, Shantanu Aggarwal, Vincent Zhang, Meghana Missula, Rachel Liao, Zichu Li, Xiao Bai, Yunzhi Zhou, Yajun Wang, Zhe Liu, Jinchao Li, Yu Zhang

专题命中 检索器与排序 ：hybrid retrieval(title)；分类 cs.IR、cs.CL

AI总结 研究动态产品广告中重定向和开拓新客户的平衡问题，提出SMART方法，通过规则与LLM生成查询结合及质量门控管理成本，经实验验证，该方法有效提升广告转化率，降低LLM成本。

Comments To be published in the 20th ACM Conference on Recommender Systems (recsys'26), September 27 - October 2, 2026, Minneapolis, MN, USA

Retrieval-Augmented Generation of Ontologies from Relational Databases

从关系数据库中检索增强生成本体

Nadeen Fathallah, Mojtaba Nayyeri, Athish A Yogi, Ratan Bahadur Thapa, Hans-Michael Tautenhahn, Anton Schnurpel, Steffen Staab

机构 * Institute for Artificial Intelligence, University of Stuttgart（人工智能研究所，斯图加特大学） ； University of Southampton（南安普顿大学） ； Universitätsklinikum Leipzig（莱比锡大学医院） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title)；分类 cs.AI、cs.DB

AI总结 研究从关系数据库生成语义丰富的OWL2DL本体的问题，提出RIGOR方法，通过大语言模型驱动，从多源检索并迭代生成本体片段，经验证和纠正后集成，实验表明该方法优于基线且无需人工监督。

Comments Accepted in ISWC26

mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

mamabench 和 mamaretrieval：评估孕产妇、新生儿和生殖健康领域医学检索增强生成的基准

Yi Ren

机构 * École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院洛桑校区） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title)；分类 cs.IR、cs.CL

AI总结 针对助产士咨询的孕产妇、新生儿和生殖健康问题，构建了包含25,949个问题的QA基准mamabench和基于3,185个查询的段落级相关性基准mamaretrieval，采用分级相关标注和标签质量审计。

Comments 13 pages, 3 tables. Datasets and construction code linked in the paper

ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

ScoreGate: 通过双分数统计融合实现检索增强生成的自适应分块选择

Karamvir Singh, Arvind Jain

机构 * HighLevel, Inc.（HighLevel公司） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title)；分类 cs.IR、cs.CL

AI总结 针对固定K检索导致过检索或欠检索的问题，提出ScoreGate，利用双编码器相似度和交叉编码器重排序分数进行自适应检索数量控制，无需额外模型调用，在MS MARCO上以更少块数提升MRR@10，并实现零假阳性。

Comments 20 pages, 6 figures, 14 tables

LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots

LERA：基于大语言模型的生成聊天机器人广告拍卖

Haoran Sun, Xinrui Song, Xinyu Zhang, Zhaohua Chen, Xu Chu, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Xiaotie Deng

机构 * Peking University（北京大学） ； Alibaba Group（阿里巴巴集团） ； Shandong University（山东大学） 纠错

专题命中 检索器与排序 ：RAG(title)；分类 cs.IR、cs.AI

AI总结 LERA提出一种两阶段检索生成拍卖框架，通过嵌入粗过滤和LLM提示生成优化广告相关性评分，提升广告选择准确性和多样性。

Comments Work in Progress

MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever

MPFormer：面向工业多任务个性化序列检索的自适应框架

Yijia Sun, Shanshan Huang, Linxiao Che, Haitao Lu, Qiang Luo, Kun Gai, Guorui Zhou

机构 * Kuaishou Technology（快手科技） ； Unaffiliated（无隶属） 纠错

专题命中 检索器与排序 ：retriever(title)；分类 cs.IR、cs.AI

AI总结 本文提出MPFormer框架，通过三项创新机制解决多阶段优化不一致问题，提升推荐系统用户参与度和系统效率。

Comments CIKM 2025

Journal ref Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM '25), November 10--14, 2025, Seoul, Republic of Korea

Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval

连续空间中密集检索的无监督语料库污染攻击

Yongkang Li, Panagiotis Eustratiadis, Simon Lupart, Evangelos Kanoulas

专题命中 检索器与排序 ：dense retrieval(title)；分类 cs.IR、cs.CL

AI总结 本文提出在连续嵌入空间中进行无监督语料库污染攻击的方法，通过优化保持文档嵌入几何距离和最大化词级差异，提升攻击效率和效果，实验验证了其在不同领域数据集上的有效性。

Comments This paper has been accepted as a full paper at SIGIR 2025 and will be presented orally

A Systematic Analysis of Large Language Models with RAG-enabled Dynamic Prompting for Medical Error Detection and Correction

基于RAG动态提示的大型语言模型系统分析：用于医疗错误检测与纠正

Farzad Ahmed, Joniel Augustine Jerome, Meliha Yetisgen, Özlem Uzuner

机构 * George Mason University（乔治·马歇尔大学） ； University of Washington（华盛顿大学） 纠错

专题命中 检索器与排序 ：RAG(title)；分类 cs.CL、cs.AI

AI总结 本文提出基于RAG动态提示的医疗错误检测与纠正方法，通过对比不同提示策略，发现RDP在准确率、召回率和纠错可靠性方面表现更优。

Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG

Harshit Nainwani, Hediyeh Baban

机构 * Services AI Research Group, Dell Technologies（Dell Technologies人工智能服务研究组） 纠错

专题命中 检索器与排序 ：RAG(title)；分类 cs.IR、cs.AI

Comments 22 pages, 2 figures, technical framework paper

Trove: A Flexible Toolkit for Dense Retrieval

Reza Esfandiarpoor, Max Zuo, Stephen H. Bach

专题命中 检索器与排序 ：dense retrieval(title)；分类 cs.IR、cs.AI

Your Dense Retriever is Secretly an Expeditious Reasoner

Yichi Zhang, Jun Bai, Zhixin Cai, Shuhan Qin, Zhuofan Chen, Jinghua Guan, Wenge Rong

机构 * School of Computer Science and Engineering, Beihang University, China（北京航空航天大学计算机科学与工程学院） ； Beijing Institute for General Artificial Intelligence, China（北京通用人工智能研究院） 纠错

专题命中 检索器与排序 ：retriever(title)；分类 cs.IR、cs.AI

Comments 16 pages, 11 figures