AI 大模型

RAG / 检索增强生成

检索增强生成、向量检索、知识库问答和面向大模型的搜索系统。

2025-09-23 至 2025-09-23 共收录 5 篇信号源：cs.IR, cs.CL, cs.AI, cs.DB

1. 知识库问答 5 篇

2506.20608 2025-09-23 cs.AI cs.NA math.NA 70%

AI Assistants to Enhance and Exploit the PETSc Knowledge Base

Barry Smith, Junchao Zhang, Hong Zhang, Lois Curfman McInnes, Murat Keceli, Archit Vasan, Satish Balay, Toby Isaac, Le Chen, Venkatram Vishwanath

机构 * Flatiron Institute, Simons Foundation（Flatiron研究所、Simons基金会）； Argonne National Laboratory（阿贡国家实验室）

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

Journal ref 54th International Conference on Parallel Processing Companion (ICPP Companion '25), 2025

2506.00608 2025-09-23 cs.CL 70%

PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements

Petros Raptopoulos, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou

机构 * School of Electrical and Computer Engineering, AILS Laboratory, National Technical University of Athens（电气与计算机工程学院，AILS实验室，国家技术大学雅典）； Instituto de Telecomunicações（电信研究所）

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

Comments Accepted at EMNLP 2025

2509.17788 2025-09-23 cs.CL cs.AI 62%

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

2503.01606 2025-09-23 cs.CL cs.AI cs.CY cs.LG 62%

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）

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/

2506.11474 2025-09-23 cs.CL 57%

Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards

Jaehoon Yun, Jiwoong Sohn, Jungwoo Park, Hyunjae Kim, Xiangru Tang, Yanjun Shao, Yonghoe Koo, Minhyeok Ko, Qingyu Chen, Mark Gerstein, Michael Moor, Jaewoo Kang

机构 * Korea University（韩国大学）； ETH Zürich（苏黎世联邦理工学院）； Yale University（耶鲁大学）； AIGEN Sciences（AIGEN公司）； Hanyang University College of Medicine（翰雅大学医学院）； University of Ulsan College of Medicine（釜山大学医学院）

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

Comments Accepted to EMNLP 2025 (Oral)