RAG / 检索增强生成

MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance

Jihye Choi, Nils Palumbo, Prasad Chalasani, Matthew M. Engelhard, Somesh Jha, Anivarya Kumar, David Page

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

Comments Paper published at Machine Learning for Healthcare 2024 (MLHC'24)

Faculty Perspectives on the Potential of RAG in Computer Science Higher Education

Sagnik Dakshit

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval augmented generation(abstract)

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Mintong Kang, Nezihe Merve Gürel, Ning Yu, Dawn Song, Bo Li

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

Comments Accepted to ICML 2024

ESAC (EQ-SANS Assisting Chatbot): Application of Large Language Models and Retrieval-Augmented Generation for Enhanced User Experience at EQ-SANS

Changwoo Do, Gergely Nagy, William T. Heller

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

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

Zhiyuan Peng, Xuyang Wu, Qifan Wang, Yi Fang

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

Comments Under Reivew

TelecomRAG: Taming Telecom Standards with Retrieval Augmented Generation and LLMs

Girma M. Yilma, Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez

专题命中 检索器与排序 ：retrieval augmented generation(title)；retrieval-augmented generation(abstract)；RAG(abstract)

Comments 7 pages, 2 figures, 3 tables

Retrieval Augmented Generation for Domain-specific Question Answering

Sanat Sharma, David Seunghyun Yoon, Franck Dernoncourt, Dewang Sultania, Karishma Bagga, Mengjiao Zhang, Trung Bui, Varun Kotte

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

Comments AAAI 2024 (Association for the Advancement of Artificial Intelligence) Scientific Document Understanding Workshop

RaFe: Ranking Feedback Improves Query Rewriting for RAG

Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

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

Comments 16 pages

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

Nandan Thakur, Jianmo Ni, Gustavo Hernández Ábrego, John Wieting, Jimmy Lin, Daniel Cer

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

Comments Accepted at NAACL 2024. Data released at https://github.com/google-research-datasets/swim-ir

Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation

Zifei FeiFei Han, Jionghao Lin, Ashish Gurung, Danielle R. Thomas, Eason Chen, Conrad Borchers, Shivang Gupta, Kenneth R. Koedinger

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

Comments 11 page Workshop paper, AAAI2024 Workshop on AI for Education - Bridging Innovation and Responsibility, Large Language Model, Personalized Tutor Training, Automatic Assessment

Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning

Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu

专题命中 检索器与排序 ：retrieval augmented generation(title,abstract)；RAG(abstract)

Comments 6 pages

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation

Shicheng Xu, Liang Pang, Jun Xu, Huawei Shen, Xueqi Cheng

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

Comments Accepted by WWW 2024

RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation

Run-Ze Fan, Yixing Fan, Jiangui Chen, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng

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

Comments Accepted by ECIR2024 full paper

Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping

Will E. Thompson, David M. Vidmar, Jessica K. De Freitas, John M. Pfeifer, Brandon K. Fornwalt, Ruijun Chen, Gabriel Altay, Kabir Manghnani, Andrew C. Nelsen, Kellie Morland, Martin C. Stumpe, Riccardo Miotto

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

Comments Deep Generative Models for Health Workshop NeurIPS 2023

Dense Retrieval as Indirect Supervision for Large-space Decision Making

Nan Xu, Fei Wang, Mingtao Dong, Muhao Chen

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

Comments EMNLP 2023 (Findings)

Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval

Daniel Campos, ChengXiang Zhai

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

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju, Yuzhong Qu, Gong Cheng

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

Comments 9 pages, accepted by AAAI 2023

A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA

Yangyang Guo, Liqiang Nie, Yongkang Wong, Yibing Liu, Zhiyong Cheng, Mohan Kankanhalli

专题命中 检索器与排序 ：retriever(title,abstract)；knowledge retrieval(abstract)

Robust Retrieval Augmented Generation for Zero-shot Slot Filling

Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Alfio Gliozzo

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

Comments Accepted at EMNLP 2021. arXiv admin note: substantial text overlap with arXiv:2104.08610

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions

Zixian Huang, Ao Wu, Yulin Shen, Gong Cheng, Yuzhong Qu

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

Comments 10 pages, accepted to Findings of EMNLP 2021

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Wayne Xin Zhao, Yang Song, Tao Zhang

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

Comments LLM;RAG;MCTS

Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG

Gabriel de Souza P. Moreira, Ronay Ak, Benedikt Schifferer, Mengyao Xu, Radek Osmulski, Even Oldridge

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

Comments Accepted for the 1st Workshop on GenAI and RAG Systems for Enterprise @ CIKM 2024

A Fully Attention-Based Information Retriever

Alvaro Henrique Chaim Correia, Jorge Luiz Moreira Silva, Thiago de Castro Martins, Fabio Gagliardi Cozman

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

Comments Accepted for presentation at the International Joint Conference on Neural Networks (IJCNN) 2018

Journal ref A. H. C. Correia, J. L. M. Silva, T. d. C. Martins and F. G. Cozman, "A Fully Attention-Based Information Retriever," 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 2018, pp. 2799-2806

Operationalizing Cyber Threat Intelligence with GraphRAG

用GraphRAG实现网络威胁情报的操作化

Atul Kabra, Prakhar Paliwal, Manjesh K. Hanawal

专题命中 检索器与排序 ：RAG(summary_cn,abstract)；分类 cs.AI

AI总结 本研究对比微软GraphRAG与Naive RAG，发现GraphRAG生成的网络威胁情报检测方案，在攻击线索轮换后保持率远高于后者，能依赖更难规避的持久线索，为自动生成SOC狩猎方案提供了架构基础。

Comments 12 pages

EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval

EnterpriseRAG：非理想企业检索场景下LLM指令遵循与鲁棒性的基准测试

Huiqi Miao, Xinbao Sun, Bo Wang, Fanyu Meng, Lijun Mei, Na Wu, Di Jin, Chao Deng, Junlan Feng

机构 * Jiutian Research, China Mobile（中国移动九天研究院） 纠错

专题命中 检索器与排序 ：RAG(summary_cn,abstract)；分类 cs.AI

AI总结 研究针对企业RAG部署的可靠性问题，推出含983个样本的EnterpriseRAG基准，评估13个LLM发现其指令遵循崩溃，为生产级RAG提供可复现的评估基础

Training Dense Retrievers with Multiple Positive Passages

利用多正例段落训练密集检索器

Benben Wang, Minghao Tang, Hengran Zhang, Jiafeng Guo, Keping Bi

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

AI总结 本文提出利用多正例段落训练检索器，通过统一对比学习框架分析不同优化目标，发现LSEPair在鲁棒性和性能上表现优异，同时揭示了不同目标对正样本质量的敏感性。

Comments Accepted by KDD 2026

Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management

作为监管知识管理认知计算架构组件的检索增强大语言模型

Dariusz Nowak-Nova

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

AI总结 研究探讨将大语言模型与检索增强生成架构集成用于监管知识管理，提出本地部署LLMs的架构方法，经实验验证，此集成提升了生成文本质量，引入可审计性等，增强后的LLMs可作为认知计算基础设施的语义处理模块。

Trajectory-Aware Retrieval Agents for Temporal Decision- Making

用于时间决策的轨迹感知检索代理

Jing Wang, Jie Shen, Xing Niu

机构 * Amazon（亚马逊） 纠错

专题命中 检索器与排序 ：RAG(summary_cn,abstract)；分类 cs.AI

AI总结 研究用大语言模型代理从长篇时间结构化文本中决策的问题，针对标准RAG丢弃时间结构缺陷，引入闭环代理框架TLM，其关键技术是LGCM，在医学问答、收益电话会议惊喜预测和隔夜股票缺口预测任务中表现出色。

Evidence-in-the-Loop: Trace-Driven Optimization for Customer-Service LLM Agents

循证优化：面向客户服务语言模型代理的跟踪驱动优化

Chunming Wu, Dafei Qiu, Congde Yuan, Charles Quan, Jun Wu, Suipeng Li, Mo Wu, Gavin Xie, Hope Chen, Max Yao

专题命中 检索器与排序 ：RAG(summary_cn,abstract)；分类 cs.IR

AI总结 研究面向客户服务语言模型代理的优化，提出循证客户服务代理工作流程，通过多种技术构建证据，结合政策引导编排。贡献混合RAG证据构建、循证问题/行动决策、跟踪驱动的RAG和重排器改进三种部署模式。

Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support

证据接口塑造了检索增强型读者使用支持信息的方式

Junchi Liao, Jiawen Deng, Fuji Ren

专题命中 检索器与排序 ：RAG(summary_cn,abstract)；分类 cs.AI

AI总结 研究多跳 RAG 评估中前 k 答案分数隐藏的问题，通过对比不同训练方式的适配读者，区分支持可用性失败与读者接口效应，并指出在支持标注评估中应同时报告前 k 答案分数与完整支持覆盖率，黄金支持优先等方法可改进读者。

Comments 18 pages; includes references and appendices