RAG / 检索增强生成 - arXivDaily 专题

2410.13339 2025-02-28 cs.CL 83%

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

Ingeol Baek, Hwan Chang, Byeongjeong Kim, Jimin Lee, Hwanhee Lee

机构 * Chung-Ang University（中央大学）

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

Comments NAACL 2025 Findings

2502.17888 2025-02-26 cs.CL 83%

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Mingyan Wu, Zhenghao Liu, Yukun Yan, Xinze Li, Shi Yu, Zheni Zeng, Yu Gu, Ge Yu

机构 * Northeastern University（东北大学）； Tsinghua University（清华大学）

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

2502.15722 2025-02-26 cs.IR cs.HC 83%

Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers

Axum AI, :, J. Owoyemi, S. Abubakar, A. Owoyemi, T. O. Togunwa, F. C. Madubuko, S. Oyatoye, Z. Oyetolu, K. Akyea, A. O. Mohammed, A. Adebakin

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

Comments 4 pages, 2 tables and 3 figures

2502.17390 2025-02-25 cs.CL cs.LG 83%

Mitigating Bias in RAG: Controlling the Embedder

Taeyoun Kim, Jacob Springer, Aditi Raghunathan, Maarten Sap

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

Comments 26 pages (8 main), 12 figures, 7 tables

2502.16573 2025-02-25 cs.AI cs.LG 83%

LawPal : A Retrieval Augmented Generation Based System for Enhanced Legal Accessibility in India

Dnyanesh Panchal, Aaryan Gole, Vaibhav Narute, Raunak Joshi

机构 * Vidyavardhini’s College of Engineering and Technology（维迪亚瓦尔迪尼工程技术学院）

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

2412.15605 2025-02-25 cs.CL 83%

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks

Brian J Chan, Chao-Ting Chen, Jui-Hung Cheng, Hen-Hsen Huang

机构 * National Chengchi University（国立政治大学）； Academia Sinica（中央研究院）

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

Comments 5 pages, accepted by the Web Conference 2025 (WWW '25) as a short paper

2408.02854 2025-02-19 cs.IR 83%

Creating a Taxonomy for Retrieval Augmented Generation Applications

Irina Nikishina, Özge Sevgili, Mahei Manhai Li, Chris Biemann, Martin Semmann

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

2502.11770 2025-02-18 cs.AI 83%

Cognitive-Aligned Document Selection for Retrieval-augmented Generation

Bingyu Wan, Fuxi Zhang, Zhongpeng Qi, Jiayi Ding, Jijun Li, Baoshi Fan, Yijia Zhang, Jun Zhang

机构 * Dalian Maritime University（大连海事大学）

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

2502.10993 2025-02-18 cs.CL cs.LG 83%

RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization

Tianci Liu, Haoxiang Jiang, Tianze Wang, Ran Xu, Yue Yu, Linjun Zhang, Tuo Zhao, Haoyu Wang

机构 * Rutgers University（罗格斯大学）； Georgia Institute of Technology（佐治亚理工学院）

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

2502.08178 2025-02-13 cs.CL 83%

ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation

Ruobing Yao, Yifei Zhang, Shuang Song, Yuhua Liu, Neng Gao, Chenyang Tu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； School of Cybersecurity, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）； Alibaba Group（阿里巴巴集团）

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

2502.06652 2025-02-11 cs.CL 83%

Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A

Anna Leschanowsky, Zahra Kolagar, Erion Çano, Ivan Habernal, Dara Hallinan, Emanuël A. P. Habets, Birgit Popp

机构 * Fraunhofer Institute for Integrated Circuits (IIS)（弗劳恩霍夫集成电路研究所）； Ruhr University Bochum（波鸿鲁尔大学）； Research Center Trustworthy Data Science and Security（可信数据科学与安全研究中心）； FIZ Karlsruhe - Leibniz Institute for Information Infrastructure（卡尔斯鲁厄FIZ - 莱布尼茨信息基础设施研究所）； International Audio Laboratories Erlangen（埃尔朗根国际音频实验室）

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

Comments Submitted to ARR

2410.13192 2025-02-11 cs.CL 83%

Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models

Jiatao Li, Xinyu Hu, Xunjian Yin, Xiaojun Wan

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

Comments Accepted by NAACL 2025 (Findings). (Long Paper)

2502.04666 2025-02-10 cs.IR 83%

Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy

Rishabh Uapadhyay, Marco Viviani

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

2502.04360 2025-02-10 cs.CL cs.CR cs.LG 83%

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction

Xiao Hu, Eric Liu, Weizhou Wang, Xiangyu Guo, David Lie

机构 * University of Toronto（多伦多大学）

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

2501.17397 2025-01-30 cs.CL 83%

Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains

Subhankar Maity, Aniket Deroy, Sudeshna Sarkar

机构 * IIT Kharagpur（印度理工学院卡哈拉格普尔分校）

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

Comments Accepted at the 16th Meeting of the Forum for Information Retrieval Evaluation as a Regular Paper

2501.15290 2025-01-28 cs.CR cs.AI 83%

Advanced Real-Time Fraud Detection Using RAG-Based LLMs

Gurjot Singh, Prabhjot Singh, Maninder Singh

机构 * University of Waterloo（滑铁卢大学）； Thapar Institute of Engineering and Technology（塔帕尔工程技术学院）

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

2501.14998 2025-01-28 cs.CL 83%

Federated Retrieval Augmented Generation for Multi-Product Question Answering

Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, Yunyao Li

机构 * Virginia Tech（弗吉尼亚理工大学）； Adobe（奥多比公司）

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

2501.06713 2025-01-28 cs.AI 83%

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

Tianyu Fan, Jingyuan Wang, Xubin Ren, Chao Huang

机构 * University of Hong Kong（香港大学）

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

2407.01158 2025-01-28 cs.CL 83%

Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation

Takyoung Kim, Kyungjae Lee, Young Rok Jang, Ji Yong Cho, Gangwoo Kim, Minseok Cho, Moontae Lee

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； LG AI Research（LG AI研究院）； Cornell University（康奈尔大学）； Korea University（高丽大学）； University of Illinois Chicago（芝加哥伊利诺伊大学）

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

Comments NAACL 2025 (Findings, Long). Resources are available at https://github.com/youngerous/qtree

2412.19291 2025-01-23 cs.LG cs.AI cs.CR 83%

RAG with Differential Privacy

Nicolas Grislain

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

2501.11440 2025-01-22 cs.CL 83%

RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles

Jonathan Lin, Aditya Joshi, Hye-young Paik, Tri Dung Doung, Deepti Gurdasani

机构 * University of New South Wales（新南威尔士大学）

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

Comments Accepted at WWW 2025 as a short paper. 4 pages with references

2408.11775 2025-01-17 cs.CL cs.NI 83%

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

Omar Erak, Nouf Alabbasi, Omar Alhussein, Ismail Lotfi, Amr Hussein, Sami Muhaidat, Merouane Debbah

机构 * Khalifa University（哈利法大学）； Carleton University（卡尔顿大学）

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

Comments submitted to Proc. IEEE Globecom

2501.04858 2025-01-10 cs.CL 83%

Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization

Sara Bourbour Hosseinbeigi, Sina Asghari, Mohammad Ali Seif Kashani, Mohammad Hossein Shalchian, Mohammad Amin Abbasi

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

2501.04695 2025-01-09 cs.LG cs.CV cs.IR cs.IT math.IT 83%

Re-ranking the Context for Multimodal Retrieval Augmented Generation

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar, Sennur Ulukus

机构 * University of Maryland College Park（马里兰大学帕克分校）； NEC Laboratories America（美国NEC实验室）

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

2411.16133 2025-01-07 cs.LG cs.IR 83%

Context Awareness Gate For Retrieval Augmented Generation

Mohammad Hassan Heydari, Arshia Hemmat, Erfan Naman, Afsaneh Fatemi

机构 * University of Isfahan（伊斯法罕大学）

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

2411.06175 2024-12-30 cs.CL cs.LG 83%

Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs

Shan Zhong, Jiahao Zeng, Yongxin Yu, Bohong Lin

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

2412.17250 2024-12-24 cs.IR 83%

SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval

Xiaopeng Li, Xiangyang Li, Hao Zhang, Zhaocheng Du, Pengyue Jia, Yichao Wang, Xiangyu Zhao, Huifeng Guo, Ruiming Tang

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

2412.16643 2024-12-24 cs.AI 83%

TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation

Silin Yang, Dong Wang, Haoqi Zheng, Ruochun Jin

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

2412.13163 2024-12-20 cs.DC cs.IR 83%

C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System

Parker Addison, Minh-Tuan H. Nguyen, Tomislav Medan, Jinali Shah, Mohammad T. Manzari, Brendan McElrone, Laksh Lalwani, Aboli More, Smita Sharma, Holger R. Roth, Isaac Yang, Chester Chen, Daguang Xu, Yan Cheng, Andrew Feng, Ziyue Xu

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

2412.12775 2024-12-18 cs.IR cs.CR 83%

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service

Yihang Cheng, Lan Zhang, Junyang Wang, Mu Yuan, Yunhao Yao

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

1. 检索器与排序 4608 篇

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers

Mitigating Bias in RAG: Controlling the Embedder

LawPal : A Retrieval Augmented Generation Based System for Enhanced Legal Accessibility in India

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks

Creating a Taxonomy for Retrieval Augmented Generation Applications

Cognitive-Aligned Document Selection for Retrieval-augmented Generation

RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization

ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation

Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A

Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models

Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction

Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains

Advanced Real-Time Fraud Detection Using RAG-Based LLMs

Federated Retrieval Augmented Generation for Multi-Product Question Answering

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation

RAG with Differential Privacy

RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization

Re-ranking the Context for Multimodal Retrieval Augmented Generation

Context Awareness Gate For Retrieval Augmented Generation

Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs

SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval

TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation

C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service