RAG / 检索增强生成 - arXivDaily 专题

2503.03108 2025-07-23 cs.CR cs.AI 70%

OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting

Wenrui Cheng, Tiantian Zhu, Shunan Jing, Jian-Ping Mei, Mingjun Ma, Jiaobo Jin, Zhengqiu Weng

机构 * Zhejiang University of Technology（浙江工业大学）； Wenzhou University of Technology（温州大学）

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

2505.02304 2025-07-23 cs.CL cs.CV 70%

Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition

Siyu Liang, Yunan Li, Wentian Xin, Huizhou Chen, Xujie Liu, Kang Liu, Qiguang Miao

机构 * Xidian University（西安电子科技大学）

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

Comments 9 pages, 6 figures

2507.15025 2025-07-22 cs.SE cs.AI 70%

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code

Nenad Petrovic, Vahid Zolfaghari, Andre Schamschurko, Sven Kirchner, Fengjunjie Pan, Chengdng Wu, Nils Purschke, Aleksei Velsh, Krzysztof Lebioda, Yinglei Song, Yi Zhang, Lukasz Mazur, Alois Knoll

机构 * Chair of Robotics, Artificial Intelligence and Real-Time Systems（机器人、人工智能与实时系统教授席）

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

Comments Conference paper accepted for GACLM 2025

2507.14849 2025-07-22 cs.CL 70%

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

Yifei Wang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）

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

2507.09985 2025-07-15 cs.RO cs.AI 70%

Demonstrating the Octopi-1.5 Visual-Tactile-Language Model

Samson Yu, Kelvin Lin, Harold Soh

机构 * Dept. of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）； NUS Smart Systems Institute（新加坡国立大学智能系统研究所）

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

Comments Published at R:SS 2025

2410.06949 2025-07-09 cs.SE cs.CL 70%

Towards Exception Safety Code Generation with Intermediate Representation Agents Framework

Xuanming Zhang, Yuxuan Chen, Yuan Yuan, Minlie Huang

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； Stanford University（斯坦福大学）； Tsinghua University（清华大学）； Beihang University（北航大学）

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

2507.02975 2025-07-08 cs.LG cs.IR 70%

Introducing Answered with Evidence -- a framework for evaluating whether LLM responses to biomedical questions are founded in evidence

Julian D Baldwin, Christina Dinh, Arjun Mukerji, Neil Sanghavi, Saurabh Gombar

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

Comments 17 pages; 3 figures; 3 main tables. This work will be submitted for full publication shortly;wanted to share ahead of industry conference

2507.02760 2025-07-04 cs.AI 70%

Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work

Guangwei Zhang

机构 * School of History and Civilization, Shaanxi Normal University（历史与文明学院，陕西师范大学）

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

2506.22703 2025-07-01 cs.SE cs.AI 70%

P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code

Wali Mohammad Abdullah, Azmain Kabir

机构 * Mathematics \& Information Technology Concordia University of Edmonton Edmonton, Alberta, Canada ； Computer Science University of Manitoba Winnipeg, Manitoba, Canada

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

2506.22210 2025-06-30 cs.IR 70%

UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses

Weronika Łajewska, Ivica Kostric, Gabriel Iturra-Bocaz, Mariam Arustashvili, Krisztian Balog

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

2409.09510 2025-06-27 cs.CL 70%

Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models

Alireza Salemi, Hamed Zamani

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

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

2506.20598 2025-06-26 cs.AI cs.SY eess.SY 70%

Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges

Alexander D. Kalian, Jaewook Lee, Stefan P. Johannesson, Lennart Otte, Christer Hogstrand, Miao Guo

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

2506.20415 2025-06-26 cs.CR cs.AI cs.MA 70%

SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models

Dipayan Saha, Shams Tarek, Hasan Al Shaikh, Khan Thamid Hasan, Pavan Sai Nalluri, Md. Ajoad Hasan, Nashmin Alam, Jingbo Zhou, Sujan Kumar Saha, Mark Tehranipoor, Farimah Farahmandi

机构 * Department of Electrical and Computer Engineering, University of Florida（电子与计算机工程系，佛罗里达大学）

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

2502.20330 2025-06-24 cs.CL 70%

RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

Guanzheng Chen, Qilong Feng, Jinjie Ni, Xin Li, Michael Qizhe Shieh

机构 * National University of Singapore（新加坡国立大学）； DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）； Hupan Lab, 310023, Hangzhou, China（杭州研究院）

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

Comments ICML 2025 Spotlight

2506.14336 2025-06-18 cs.AI 70%

AviationLLM: An LLM-based Knowledge System for Aviation Training

Jia'ang Wan, Feng Shen, Fujuan Li, Yanjin Sun, Yan Li, Shiwen Zhang

机构 * Wuhan University（武汉大学）； China Eastern Technology Application Research And Development Center Co., Ltd（中国东方技术应用研发有限公司）

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

2506.13607 2025-06-17 cs.IR 70%

Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations

Chia-Heng Yu, Yen-Lung Tsai

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

Comments 19 pages, 5 figures, Code available at https://github.com/arthur422tp/hierachical

2410.04194 2025-06-16 cs.CL cs.FL 70%

Consistent Autoformalization for Constructing Mathematical Libraries

Lan Zhang, Xin Quan, Andre Freitas

机构 * Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系）； Idiap Research Institute（Idiap研究 institute）； National Biomarker Centre, CRUK Manchester Institute（国家生物标志物中心，CRUK曼彻斯特研究所）

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

Comments EMNLP 2024 camera-ready

2506.07785 2025-06-10 cs.CV cs.AI cs.LG 70%

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Qi Yang, Chenghao Zhang, Lubin Fan, Kun Ding, Jieping Ye, Shiming Xiang

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences, China（中国科学院大学人工智能学院）； MAIS, Institute of Automation, Chinese Academy of Sciences, China（中国科学院自动化研究所MAIS部）； Alibaba Cloud Computing, China（阿里巴巴云计算）

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

Comments ICML 2025 Spotlight. 22 pages, 16 figures

2506.06500 2025-06-10 cs.CL 70%

Improving LLM-Powered EDA Assistants with RAFT

Luyao Shi, Michael Kazda, Charles Schmitter, Hemlata Gupta

机构 * IBM Research San Jose, CA（IBM桑 Jose研究院）； IBM Infrastructure Poughkeepsie, NY（IBM基础设施部）

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

Comments Accepted paper at IEEE International Conference on LLM-Aided Design, 2025 (LAD 2025)

2505.21919 2025-05-29 cs.ET cs.AI cs.DC 70%

Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference

Yue Zhu, Hao Yu, Chen Wang, Zhuoran Liu, Eun Kyung Lee

机构 * IBM T. J. Watson Research Center（IBM T. J. Watson研究院）

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

Comments This paper has been accepted at IEEE Cloud 2025 as WIP paper. The final version will appear in IEEE Xplore

2505.21604 2025-05-29 cs.CY cs.AI cs.HC 70%

Public Discourse Sandbox: Facilitating Human and AI Digital Communication Research

Kristina Radivojevic, Caleb Reinking, Shaun Whitfield, Paul Brenner

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

2504.05104 2025-05-29 cs.CL 70%

AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments

Saeid Ario Vaghefi, Aymane Hachcham, Veronica Grasso, Jiska Manicus, Nakiete Msemo, Chiara Colesanti Senni, Markus Leippold

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

2505.20266 2025-05-27 cs.AI cs.LG 70%

syftr: Pareto-Optimal Generative AI

Alexander Conway, Debadeepta Dey, Stefan Hackmann, Matthew Hausknecht, Michael Schmidt, Mark Steadman, Nick Volynets

机构 * DataRobot

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

Comments International Conference on Automated Machine Learning (AutoML) 2025

2505.18597 2025-05-27 cs.AI cs.LG stat.AP 70%

LLMs for Supply Chain Management

Haojie Wang, Jiuyun Jiang, L. Jeff Hong, Guangxin Jiang

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

2505.17447 2025-05-26 cs.CL 70%

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao

机构 * First Author Affiliation（第一作者机构）； Second Author Affiliation（第二作者机构）

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

Comments preprint, under review

2407.01796 2025-05-26 cs.CL 70%

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Sirui Xia, Xintao Wang, Jiaqing Liang, Yifei Zhang, Weikang Zhou, Jiaji Deng, Fei Yu, Yanghua Xiao

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

Comments Accepted to NAACL 2025 Findings

2402.00746 2025-05-26 cs.CL 70%

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System

Qinkai Yu, Mingyu Jin, Dong Shu, Chong Zhang, Lizhou Fan, Wenyue Hua, Suiyuan Zhu, Yanda Meng, Zhenting Wang, Mengnan Du, Yongfeng Zhang

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

Comments Accepted by ACL 2025 NLP4PosImpact Workshop

2412.15540 2025-05-22 cs.CL 70%

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering

Zhang Siyue, Xue Yuxiang, Zhang Yiming, Wu Xiaobao, Luu Anh Tuan, Zhao Chen

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

2409.09493 2025-05-20 cs.CR cs.AI 70%

Hacking, The Lazy Way: LLM Augmented Pentesting

Dhruva Goyal, Sitaraman Subramanian, Aditya Peela, Nisha P. Shetty

机构 * BugBase Security（BugBase安全公司）； MIT, Manipal University（MIT曼谷大学）

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

Comments This work has been submitted to the IEEE for possible publication. Nisha P. Shetty has been added as an author as the new version includes work under her supervision, enhancing the research. Significant changes have been made in the methodology, survey, and introduction sections

2505.11908 2025-05-20 cs.CL 70%

ELITE: Embedding-Less retrieval with Iterative Text Exploration

Zhangyu Wang, Siyuan Gao, Rong Zhou, Hao Wang, Li Ning

机构 * University of Southern California（南加州大学）； Jilin University（吉林大学）； National Supercomputing Center in Shenzhen（深圳国家超算中心）； Wuhan University（武汉大学）； Stellaris AI Limited（Stellaris AI有限公司）

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

1. 检索器与排序 4552 篇

OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting

Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

Demonstrating the Octopi-1.5 Visual-Tactile-Language Model

Towards Exception Safety Code Generation with Intermediate Representation Agents Framework

Introducing Answered with Evidence -- a framework for evaluating whether LLM responses to biomedical questions are founded in evidence

Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work

P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code

UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses

Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models

Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges

SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models

RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

AviationLLM: An LLM-based Knowledge System for Aviation Training

Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations

Consistent Autoformalization for Constructing Mathematical Libraries

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Improving LLM-Powered EDA Assistants with RAFT

Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference

Public Discourse Sandbox: Facilitating Human and AI Digital Communication Research

AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments

syftr: Pareto-Optimal Generative AI

LLMs for Supply Chain Management

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering

Hacking, The Lazy Way: LLM Augmented Pentesting

ELITE: Embedding-Less retrieval with Iterative Text Exploration