RAG / 检索增强生成

RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering

RVR：用于综合问答的检索-验证-检索

Deniz Qian, Hung-Ting Chen, Eunsol Choi

机构 * Courant Institute School of Mathematics, Computing, and Data Science, New York University（纽约大学Courant研究所数学、计算与数据科学学院） ； Courant Institute School of Mathematics, Computing（纽约大学Courant研究所数学、计算与数据科学学院） ； Data Science, New York University（纽约大学数据科学学院） 纠错

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

AI总结 RVR提出了一种多轮检索框架，通过验证器和检索器优化，提升多答案检索的召回率和覆盖范围。

Comments 18 pages, 12 figures, 12 tables

Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content

超越事实问答：面向长形式多语言内容的指导型问答

Parth Bhalerao, Diola Dsouza, Ruiwen Guan, Oana Ignat

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

AI总结 本文提出MentorQA，首个多语言长形式视频指导型问答数据集和评估框架，通过对比不同架构发现Multi-Agent在复杂和低资源语言中表现更优。

Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs

通过检索增强的大语言模型中的原子事实核查来提高医疗问答的可靠性与可解释性

Juraj Vladika, Annika Domres, Mai Nguyen, Rebecca Moser, Jana Nano, Felix Busch, Lisa C. Adams, Keno K. Bressem, Denise Bernhardt, Stephanie E. Combs, Kai J. Borm, Florian Matthes, Jan C. Peeken

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

AI总结 通过原子事实核查提升医疗问答的可靠性与可解释性，减少幻觉并提高事实准确性。

Comments 18 pages, 7 figures and tables

Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?

检索增强型问答：当LLMs应承认无知时

Dingmin Wang, Ji Ma, Shankar Kumar

机构 * Google Research（谷歌研究） ； University of Oxford（牛津大学） 纠错

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

AI总结 本文提出了一种自适应提示策略，通过分割检索信息并逐步提示LLM回答问题，以提高问答性能并减少无关信息的影响。

Question Answering for Decisionmaking in Green Building Design: A Multimodal Data Reasoning Method Driven by Large Language Models

绿色建筑设计中的决策制定问答：一种由大语言模型驱动的多模态数据推理方法

Yihui Li, Xiaoyue Yan, Hao Zhou, Borong Lin

机构 * School of Architecture（建筑学院） ； Tsinghua University（清华大学） 纠错

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

AI总结 本研究提出GreenQA，一种由大语言模型驱动的多模态数据推理方法，用于提升绿色建筑设计决策效率。

Comments Published at Association for Computer Aided Design in Architecture (ACADIA) 2024

Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering

Yihua Zhu, Qianying Liu, Akiko Aizawa, Hidetoshi Shimodaira

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

Comments AAAI2026 Main Track

A Hybrid Search for Complex Table Question Answering in Securities Report

Daiki Shirafuji, Koji Tanaka, Tatsuhiko Saito

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

Comments Accepted to IIAI AAI 2025

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Bohan Yu, Wei Huang, Kang Liu

机构 * Baidu（百度） 纠错

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

Comments Accepted by AAAI 2026

Continual Dialogue State Tracking via Example-Guided Question Answering

Hyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Raghavi Chandu, Satwik Kottur, Jing Xu, Jonathan May, Chinnadhurai Sankar

机构 * Information Sciences Institute, University of Southern California（美国南加州大学信息科学研究所） ； Meta AI 纠错

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

Comments 11 pages, EMNLP 2023

Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging

Hongjin Qian, Zheng Liu

机构 * Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

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

Comments Neurips 25, Spotlight

One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts

Xingyu Fan, Feifei Li, Wenhui Que, Hailong Li

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

Comments 7 pages

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering

Zhanghao Hu, Hanqi Yan, Qinglin Zhu, Zhenyi Shen, Yulan He, Lin Gui

机构 * King’s College London（伦敦国王学院） ； The Alan Turing Institute（艾伦·图灵研究所） 纠错

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

Comments Accepted in ACL 2025 Main, Project link: https://zhanghao-acl25-embqa.github.io/ACL2025-EmbQA/

ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs

Samira Khorshidi, Azadeh Nikfarjam, Suprita Shankar, Yisi Sang, Yash Govind, Hyun Jang, Ali Kasgari, Alexis McClimans, Mohamed Soliman, Vishnu Konda, Ahmed Fakhry, Xiaoguang Qi

机构 * Apple Inc（苹果公司） 纠错

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

EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering

Chang Zong, Jian Wan, Siliang Tang, Lei Zhang

机构 * Zhejiang University of Science and Technology（浙江理工大学） ； Zhejiang University（浙江大学） 纠错

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

Comments 13 pages, 6 figures

DeepResearch$^{\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology

Jennifer D'Souza, Endres Keno Sander, Andrei Aioanei

机构 * TIB Leibniz Information Centre for Science（图灵-莱比锡科学与技术信息中心） ； Leibniz University Hannover, Germany（莱比锡汉诺威大学） 纠错

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

Comments 12 pages, 3 figures

Knowledge-Aware Diverse Reranking for Cross-Source Question Answering

Tong Zhou

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

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

Journal ref SIGIR 2025 LiveRAG

FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models

Bithiah Yuan

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

Comments Submitted in partial fulfillment of the requirements for the Master of Science degree in Computer Science at the University of Freiburg, July 31, 2020

Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering

Yubo Wang, Xueguang Ma, Wenhu Chen

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

Comments This version has been accepted and published at EMNLP Findings 2024

iTRI-QA: a Toolset for Customized Question-Answer Dataset Generation Using Language Models for Enhanced Scientific Research

Qiming Liu, Zhongzheng Niu, Siting Liu, Mao Tian

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

Comments 13 pages, 3 figures

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

Daniel Fleischer, Moshe Berchansky, Gad Markovits, Moshe Wasserblat

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

Comments 14 pages

Dynamic Strategy Planning for Efficient Question Answering with Large Language Models

Tanmay Parekh, Pradyot Prakash, Alexander Radovic, Akshay Shekher, Denis Savenkov

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

Comments Accepted at NAACL 2025 Findings

KBLaM: Knowledge Base augmented Language Model

Xi Wang, Taketomo Isazawa, Liana Mikaelyan, James Hensman

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

Hybrid-SQuAD: Hybrid Scholarly Question Answering Dataset

Tilahun Abedissa Taffa, Debayan Banerjee, Yaregal Assabie, Ricardo Usbeck

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

Multi-Document Financial Question Answering using LLMs

Shalin Shah, Srikanth Ryali, Ramasubbu Venkatesh

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

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Luu Anh Tuan

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

Comments Accepted by Findings of ACL 2024

Journal ref ACL 2024

An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms

Ziyang Chen, Xiaobin Wang, Yong Jiang, Jinzhi Liao, Pengjun Xie, Fei Huang, Xiang Zhao

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

Comments 10 pages, 6 figures

Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering

Yanggyu Lee, Jihie Kim

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

Comments Accepted to the Trustworthy AI Workshop at IJCAI 2024

SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering

Chyi-Jiunn Lin, Guan-Ting Lin, Yung-Sung Chuang, Wei-Lun Wu, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-shan Lee

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

Comments Accepted at ICASSP 2024

Enhancing Healthcare through Large Language Models: A Study on Medical Question Answering

Haoran Yu, Chang Yu, Zihan Wang, Dongxian Zou, Hao Qin

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

Comments received by IEEE ICPICS

SyllabusQA: A Course Logistics Question Answering Dataset

Nigel Fernandez, Alexander Scarlatos, Andrew Lan

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

Comments ACL 2024: The 62nd Annual Meeting of the Association for Computational Linguistics