RAG / 检索增强生成

DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA

Yuelyu Ji, Hang Zhang, Shiven Verma, Hui Ji, Chun Li, Yushui Han, Yanshan Wang

机构 * Department of Information Science, University of Pittsburgh（信息科学系，匹兹堡大学） ； Department of Biomedical Informatics, University of Pittsburgh（生物医学信息学系，匹兹堡大学） ； Department of Health Information Management and ISP, University of Pittsburgh（健康信息管理与信息科学系，匹兹堡大学） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases

Yash Tiwari, Owais Ahmad Lone, Mayukha Pal

机构 * ABB Ability Innovation Center（ABB能力创新中心） 纠错

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.AI

NeoQA: Evidence-based Question Answering with Generated News Events

Max Glockner, Xiang Jiang, Leonardo F. R. Ribeiro, Iryna Gurevych, Markus Dreyer

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering

Yuelyu Ji, Rui Meng, Zhuochun Li, Daqing He

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant

Congrui Yin, Evan Wei, Zhongxing Zhang, Zaifu Zhan

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs

Chang Liu, Ying Chang, Jianmin Li, Yiqian Qu, Yu Li, Lingyong Cao, Shuyuan Lin

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

SenseRAG: Constructing Environmental Knowledge Bases with Proactive Querying for LLM-Based Autonomous Driving

Xuewen Luo, Fan Ding, Fengze Yang, Yang Zhou, Junnyong Loo, Hwa Hui Tew, Chenxi Liu

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

Comments This paper has been accepted for presentation at WACV Workshop LLMAD 2025

Molly: Making Large Language Model Agents Solve Python Problem More Logically

Rui Xiao, Jiong Wang, Lu Han, Na Zong, Han Wu

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Comments arXiv admin note: text overlap with arXiv:2402.07913

Domain-specific Question Answering with Hybrid Search

Dewang Sultania, Zhaoyu Lu, Twisha Naik, Franck Dernoncourt, David Seunghyun Yoon, Sanat Sharma, Trung Bui, Ashok Gupta, Tushar Vatsa, Suhas Suresha, Ishita Verma, Vibha Belavadi, Cheng Chen, Michael Friedrich

专题命中 知识库问答 ：retriever(abstract)；dense retrieval(abstract)；分类 cs.CL

Comments AAAI-25 Workshop on Document Understanding and Intelligence

MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering

Iñigo Alonso, Maite Oronoz, Rodrigo Agerri

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Journal ref Artificial Intelligence in Medicine Volume 155, September 2024, 102938

Efficient In-Domain Question Answering for Resource-Constrained Environments

Isaac Chung, Phat Vo, Arman C. Kizilkale, Aaron Reite

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Comments 6 pages, 2 tables

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild

Zhiying Zhu, Yiming Yang, Zhiqing Sun

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models

Duy Khoa Pham, Bao Quoc Vo

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Comments 9 pages

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, Bo Li

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR

Comments 22 pages, 13 figures, 7 tables

Scientific QA System with Verifiable Answers

Adela Ljajić, Miloš Košprdić, Bojana Bašaragin, Darija Medvecki, Lorenzo Cassano, Nikola Milošević

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Comments Accepted at the 6th International Open Search Symposium 2024. arXiv admin note: substantial text overlap with arXiv:2402.18589

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions

Zhebin Zhang, Xinyu Zhang, Yuanhang Ren, Saijiang Shi, Meng Han, Yongkang Wu, Ruofei Lai, Zhao Cao

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

Two-Step Question Retrieval for Open-Domain QA

Yeon Seonwoo, Juhee Son, Jiho Jin, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha, Alice Oh

专题命中 知识库问答 ：retriever(abstract)；dense retrieval(abstract)；分类 cs.CL

Comments ACL2022-Findings

EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos

EgoExoMem: 跨视角记忆推理 over 同步的自身视角和外部视角视频

Ruiping Liu, Junwei Zheng, Yufan Chen, Di Wen, Shaofang Quan, Chengzhi Wu, Jiaming Zhang, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； ETH Zurich（苏黎世联邦理工学院） ； University of Oxford（牛津大学） ； Hunan University（湖南大学） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)

AI总结 本文提出EgoExoMem，首个跨视角记忆推理基准，通过同步自身视角和外部视角视频进行跨视角记忆推理，利用E$^2$-Select方法实现高效的帧选择，实验表明自身和外部视角提供互补的记忆线索，但现有模型在基准测试中表现有限。

Comments The source code and dataset can be found at https://github.com/RuipingL/EgoExoMem

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning

ODTQA-FoRe：面向未来数据预测与推理的开放域表格问答数据集

Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

机构 * School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院） ； Institute of Artificial Intelligence and Future Networks, Beijing Normal University（北京师范大学人工智能与未来网络研究院） ； Faculty of Arts and Sciences, Beijing Normal University（北京师范大学文理学院） ； Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist大学） 纠错

专题命中 知识库问答 ：retriever(abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结 提出开放域表格问答的未来预测与推理任务，并构建首个覆盖时间序列预测和基于预测推理的数据集，通过基于LLM代理的TimeFore框架（检索器、预测器、分析器）解决历史数据检索、预测限制和响应标准化挑战。

Comments This paper has been accepted by Findings of ACL 2026

GrepSeek: Training Search Agents for Direct Corpus Interaction

GrepSeek：训练用于直接语料库交互的搜索代理

Alireza Salemi, Chang Zeng, Atharva Nijasure, Jui-Hui Chung, Razieh Rahimi, Fernando Diaz, Hamed Zamani

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； Princeton University（普林斯顿大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 知识库问答 ：retriever(abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结 提出GrepSeek，一种通过两阶段训练（冷启动数据集+GRPO优化）和语义保持的分片并行执行引擎，训练紧凑型搜索代理直接与文本语料库交互（通过shell命令），在开放域问答中取得最优F1和精确匹配。

Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering

学习搜索：一种基于决策的知识增强视觉问答代理

Zhuohong Chen, Zhenxian Wu, Yunyao Yu, Hangrui Xu, Zirui Liao, Zhifang Liu, Xiangwen Deng, Pen Jiao, Haoqian Wang

机构 * Tsinghua University（清华大学） ； University of Arizona（亚利桑那大学） ； Hefei University of Technology（合肥工业大学） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出基于决策的KB-VQA代理，通过多步骤决策过程解决视觉问答问题，改进检索与推理整合，提升对稀有实体和长尾事实的处理能力。

Question Answering for Multi-Release Systems: A Case Study at Ciena

多版本系统的问答：以Ciena为例的研究

Parham Khamsepour, Mark Cole, Ish Ashraf, Sandeep Puri, Mehrdad Sabetzadeh, Shiva Nejati

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 QAMR通过改进检索增强生成方法，提升多版本系统文档问答的准确性和效率。

Comments Accepted for publication in SANER 2026

SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA

SimpleDevQA：在开发知识问答上评估大语言模型

Jing Zhang, Lianghong Guo, Yanlin Wang, Mingwei Liu, Jiachi Chen, Yuchi Ma, Ensheng Shi, Terry Yue Zhuo, Hongyu Zhang, Zibin Zheng

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 SimpleDevQA是一个基于真实用户对话构建的多语言基准，用于评估大语言模型在开发知识问答任务中的表现，通过三阶段流程生成2740个问答对，发现代码LLM在该任务中表现更优。

Q-FSRU: Quantum-Augmented Frequency-Spectral For Medical Visual Question Answering

Rakesh Thakur, Yusra Tariq, Rakesh Chandra Joshi

机构 * Amity University（阿米蒂大学） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 12 pages (9 main + 2 references/appendix), 2 figures, conference paper submitted to ICLR 2026

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, Ji-Rong Wen

专题命中 知识库问答 ：RAG(abstract)；分类 cs.IR、cs.CL、cs.AI

Multi-hop Question Answering

Vaibhav Mavi, Anubhav Jangra, Adam Jatowt

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.IR、cs.CL、cs.AI

Comments Published at Foundations and Trends in Information Retrieval

AmQA: Amharic Question Answering Dataset

Tilahun Abedissa, Ricardo Usbeck, Yaregal Assabie

专题命中 知识库问答 ：retriever(abstract)；分类 cs.IR、cs.CL、cs.AI

Investigating Information Inconsistency in Multilingual Open-Domain Question Answering

Shramay Palta, Haozhe An, Yifan Yang, Shuaiyi Huang, Maharshi Gor

专题命中 知识库问答 ：retriever(abstract)；分类 cs.IR、cs.CL、cs.AI

Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering

Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen

专题命中 知识库问答 ：retriever(abstract)；分类 cs.IR、cs.CL、cs.AI

Comments Minor format updates. TLDR: Reranking retrieved passages by reader predictions can achieve 10~20 gains in top-1 retrieval accuracy and 1~4 gains in Exact Match (EM) without any training