RAG / 检索增强生成 - arXivDaily 专题

2511.04205 2025-11-07 cs.CL 57%

LLM-as-a-Judge is Bad, Based on AI Attempting the Exam Qualifying for the Member of the Polish National Board of Appeal

Michał Karp, Anna Kubaszewska, Magdalena Król, Robert Król, Aleksander Smywiński-Pohl, Mateusz Szymański, Witold Wydmański

机构 * Polish National Board of Appeal（波兰国家上诉委员会）

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

2511.01581 2025-11-04 cs.AI 57%

ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks

Chengzhang Yu, Zening Lu, Chenyang Zheng, Chiyue Wang, Yiming Zhang, Zhanpeng Jin

机构 * South China University of Technology（南方科技大学）； University of Science and Technology of China（中国科学技术大学）； Hefei Institutes of Physical Science（合肥物理科学研究院）

专题命中检索器与排序：RAG(abstract)；分类 cs.AI

Comments 12pages, 4figures

2511.00903 2025-11-04 cs.CL 57%

ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

Ahmed Masry, Megh Thakkar, Patrice Bechard, Sathwik Tejaswi Madhusudhan, Rabiul Awal, Shambhavi Mishra, Akshay Kalkunte Suresh, Srivatsava Daruru, Enamul Hoque, Spandana Gella, Torsten Scholak, Sai Rajeswar

机构 * ServiceNow ； York University（约克大学）； MILA - Quebec AI Institute（魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； École de technologie supérieure（卓越工程学院）

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

2511.00805 2025-11-04 cs.IR 57%

REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

Rishita Agarwal, Himanshu Singhal, Peter Baile Chen, Manan Roy Choudhury, Dan Roth, Vivek Gupta

专题命中检索器与排序：retriever(abstract)；分类 cs.IR

Comments 13 pages, 2 figures, 8 tables

2510.12872 2025-11-04 cs.MA cs.AI stat.ML 57%

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Hancheng Ye, Zhengqi Gao, Mingyuan Ma, Qinsi Wang, Yuzhe Fu, Ming-Yu Chung, Yueqian Lin, Zhijian Liu, Jianyi Zhang, Danyang Zhuo, Yiran Chen

机构 * Duke University（杜克大学）； MIT（麻省理工学院）； NVIDIA（英伟达）

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

Comments Accepted for publication in NeurIPS2025. Code is available at \url{https://github.com/FastMAS/KVCOMM}

2504.20434 2025-10-28 cs.SE cs.AI 57%

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Manish Bhattarai, Miguel Cordova, Minh Vu, Javier Santos, Ismael Boureima, Dan O'Malley

机构 * Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

专题命中检索器与排序：RAG(abstract)；分类 cs.AI

2510.22670 2025-10-28 cs.IR 57%

Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval

Xuan Lu, Haohang Huang, Rui Meng, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen

专题命中检索器与排序：retriever(abstract)；分类 cs.IR

2510.02656 2025-10-28 cs.IR 57%

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation

Qianfeng Wen, Yifan Liu, Justin Cui, Joshua Zhang, Anton Korikov, George-Kirollos Saad, Scott Sanner

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR

Comments 11 pages, 5 figures

2406.11093 2025-10-28 cs.CL 57%

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information

Zhiwei Liu, Kailai Yang, Qianqian Xie, Christine de Kock, Sophia Ananiadou, Eduard Hovy

机构 * The University of Manchester（曼彻斯特大学）； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）； The University of Melbourne（墨尔本大学）； Carnegie Mellon University（卡内基梅隆大学）

专题命中检索器与排序：RAG(abstract)；分类 cs.CL

Comments Accepted by ACL 2025 (Main)

2510.22003 2025-10-28 cs.SE cs.AI 57%

Impact and Implications of Generative AI for Enterprise Architects in Agile Environments: A Systematic Literature Review

Stefan Julian Kooy, Jean Paul Sebastian Piest, Rob Henk Bemthuis

机构 * University of Twente（特文特大学）

专题命中检索器与排序：knowledge retrieval(abstract)；分类 cs.AI

Comments 17 pages, 1 figure, 5 tables; to appear in Enterprise Design, Operations, and Computing. EDOC 2025 Workshops, Lecture Notes in Business Information Processing (LNBIP), Springer, 2025. Part of 29th International Conference on Enterprise Design, Operations, and Computing (EDOC)

2510.19873 2025-10-24 cs.LG cs.AI cs.PL 57%

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

Junfeng Gong, Zhiyi Wei, Junying Chen, Cheng Liu, Huawei Li

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； University of Chinese Academy of Sciences（中国科学院大学）； South China University of Technology（华南理工大学）

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

2510.19723 2025-10-23 cs.CL 57%

From Answers to Guidance: A Proactive Dialogue System for Legal Documents

Ashish Chouhan, Michael Gertz

机构 * Data Science Group, Institute of Computer Science, \ University, Germany

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

Comments 21 pages, 3 figures, 2 tables, 2 prompts

2510.13095 2025-10-22 cs.IR 57%

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Wenjun Peng, Sen Li, Fuyu Lv

专题命中检索器与排序：retriever(abstract)；分类 cs.IR

2505.06493 2025-10-21 cs.CR cs.AI 57%

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection

Zongze Li, Jiawei Guo, Haipeng Cai

机构 * University at Buffalo（布法罗大学）

专题命中检索器与排序：RAG(abstract)；分类 cs.AI

2510.16393 2025-10-21 cs.IR cs.LG cs.PF 57%

Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades

Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Salvatore Trani

机构 * University of Pisa（比萨大学）

专题命中检索器与排序：retriever(abstract)；分类 cs.IR

2510.15914 2025-10-21 cs.AR cs.AI cs.PL 57%

VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts

Jiayu Zhao, Song Chen

专题命中检索器与排序：retriever(abstract)；分类 cs.AI

Comments 9 pages, 5 figures

2310.11675 2025-10-21 cs.IR 57%

From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification

Hengran Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng

专题命中检索器与排序：retriever(abstract)；分类 cs.IR

Comments Fixed an error in the description

2510.15115 2025-10-20 cs.CL 57%

Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks

Kirill Semenov, Rico Sennrich

机构 * University of Zurich（苏黎世大学）

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

2502.21107 2025-10-20 cs.CL 57%

Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generation

Angelo Ziletti, Leonardo D'Ambrosi

机构 * Bayer AG（勃林格殷曼公司）

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

Comments 13 pages, 1 figure

2510.13925 2025-10-17 cs.CL cs.CR cs.NI 57%

An LLM-Powered AI Agent Framework for Holistic IoT Traffic Interpretation

Daniel Adu Worae, Spyridon Mastorakis

机构 * University of Notre Dame（内布拉斯加大学达灵顿分校）

专题命中检索器与排序：hybrid retrieval(abstract)；分类 cs.CL

2510.10517 2025-10-14 cs.PL cs.AI cs.SE 57%

ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs

Su-Hyeon Kim, Joonghyuk Hahn, Sooyoung Cha, Yo-Sub Han

专题命中检索器与排序：retriever(abstract)；分类 cs.AI

2510.06343 2025-10-14 cs.SE cs.AI cs.CR 57%

Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems

Fikret Mert Gultekin, Oscar Lilja, Ranim Khojah, Rebekka Wohlrab, Marvin Damschen, Mazen Mohamad

机构 * Chalmers University of Technology（楚德斯技术大学）； University of Gothenburg（哥德堡大学）； Carnegie Mellon University（卡内基梅隆大学）； RISE Research Institutes of Sweden（瑞典RISE研究机构）

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

Comments Accepted at Autonomous Agents in Software Engineering (AgenticSE) Workshop, co-located with ASE 2025

2510.09355 2025-10-13 cs.CL 57%

NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models

Fang Yuan, Junjie Zeng, Yue Hu, Zhengqiu Zhu, Quanjun Yin, Yuxiang Xie

机构 * College of Systems Engineering, National University of Defense Technology（系统工程学院，国防科技大学）； State Key Laboratory of Digital Intelligent Modeling and Simulation（数字智能建模与仿真国家重点实验室）； Test Center, National University of Defense Technology（测试中心，国防科技大学）

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

2510.08876 2025-10-13 cs.SE cs.AI 57%

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval

Kostiantyn Bevziuk, Andrii Fatula, Svetozar Lashin Yaroslav Opanasenko, Anna Tukhtarova, Ashok Jallepalli Pradeepkumar Sharma, Hritvik Shrivastava

专题命中检索器与排序：hybrid retrieval(abstract)；分类 cs.AI

2502.12669 2025-10-13 cs.AI 57%

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research

Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； Guangzhou Municipal Key Laboratory of Materials Informatics（广州市材料信息学重点实验室）

专题命中检索器与排序：knowledge retrieval(abstract)；分类 cs.AI

Comments EMNLP 2025 Findings; NeurIPS 2025 AI for Science Workshop

2510.07925 2025-10-10 cs.AI cs.HC 57%

Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

Rebecca Westhäußer, Wolfgang Minker, Sebatian Zepf

机构 * Ulm University（乌尔姆大学）

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

Comments 8 pages, 1 figure, 1 table

2501.11885 2025-10-10 cs.CL 57%

Med-R$^2$: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine

Keer Lu, Zheng Liang, Da Pan, Shusen Zhang, Guosheng Dong, Zhonghai Wu, Huang Leng, Bin Cui, Wentao Zhang

机构 * Center for Data Science, AAIS Peking University Beijing China（数据科学中心，北京大学北京中国）； Baichuan Inc. Beijing China（北川公司北京中国）； School of Computer Science Peking University Beijing China（计算机科学学院，北京大学北京中国）； Peking University（北京大学）； Baichuan Inc.（北川公司）

专题命中检索器与排序：RAG(abstract)；分类 cs.CL

2510.06056 2025-10-08 cs.AI 57%

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

Gang Liu, Yihan Zhu, Jie Chen, Meng Jiang

机构 * University of Notre Dame（诺丁汉大学）； MIT-IBM Watson AI Lab, IBM Research（麻省理工-IBM Watson AI实验室，IBM研究）

专题命中检索器与排序：knowledge retrieval(abstract)；分类 cs.AI

Comments 25 pages, 17 figures, 4 tables

2510.03204 2025-10-06 cs.CL 57%

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Léo Boisvert, Massimo Caccia, Jérémy Espinas, Alexandre Aussem, Véronique Eglin, Alexandre Lacoste

机构 * LIRIS - CNRS, INSA Lyon, Universite Claude Bernard Lyon 1（LIRIS - CNRS，INSA里昂，克劳德·贝尔纳大学里昂）； Esker ； ServiceNow Research（ServiceNow研究）； Mila - Quebec AI Institute（魁北克人工智能研究所）； McGill University（麦吉尔大学）； Polytechnique Montréal（蒙特利尔理工学院）

专题命中检索器与排序：retriever(abstract)；分类 cs.CL

2505.12950 2025-10-02 cs.CL 57%

GuRE:Generative Query REwriter for Legal Passage Retrieval

Daehee Kim, Deokhyung Kang, Jonghwi Kim, Sangwon Ryu, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，大韩民国）； AI Future Lab, KT, Republic of Korea（AI未来实验室，KT，大韩民国）； Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，大韩民国）

专题命中检索器与排序：retriever(abstract)；分类 cs.CL

Comments NLLP Workshop at EMNLP 2025

1. 检索器与排序 4595 篇

LLM-as-a-Judge is Bad, Based on AI Attempting the Exam Qualifying for the Member of the Polish National Board of Appeal

ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks

ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information

Impact and Implications of Generative AI for Enterprise Architects in Agile Environments: A Systematic Literature Review

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

From Answers to Guidance: A Proactive Dialogue System for Legal Documents

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection

Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades

VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts

From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification

Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks

Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generation

An LLM-Powered AI Agent Framework for Holistic IoT Traffic Interpretation

ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs

Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems

NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research

Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

Med-R$^2$: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

GuRE:Generative Query REwriter for Legal Passage Retrieval