东北大学信息检索实验室 Northeastern University Information Retrieval Lab

课题组简介

东北大学信息检索实验室隶属东北大学计算机科学与工程学院计算机科学系,由刘正皓副教授,于戈教授和谷峪教授和共同指导,致力于信息检索与大语言模型相关研究,承担多项国家级、省部级项目,在 ICLR、ACL、EMNLP、NAACL、SIGIR、WebConf 等国际国内顶级会议及期刊发表 40 余篇论文。课题组曾在美国官方标准局 TREC-COVID 文档级检索比赛第二轮无人工干预组的 25 支队伍中获第一名,技术成果被微软应用于其线上商业检索系统;联合清华大学和面壁智能研发端侧大语言模型 MiniCPM 的检索增强生成组件,发布时在 MTEB 榜单中文检索效果排名第一,相关模型在 Hugginface 平台累计下载超 32 万次;2025 年 1 月开源的 UltraRAG 工具获超 650 个星标;与阿里巴巴合作构建的用户视图流建模方法应用于 ATA 线上网站。实验室与清华大学孙茂松教授、刘洋教授、刘知远副教授课题组及启元实验室、面壁智能、阿里巴巴长期紧密合作,形成产学研主导的科研团体,在国家战略引导下致力于信息检索与大语言模型知识工程的创新性成果产出与工程转化落地。

亮点工作

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
Xinze Li, Sen Mei, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Hao Chen, Ge Yu, Zhiyuan Liu, Maosong Sun, Chenyan Xiong
Proceedings of ICLR  ·  2025  ·  CCF-Expanded
Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph
Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph
Qiushi Xiong, Zhipeng Xu, Zhenghao Liu, Mengjia Wang, Zulong Chen, Yue Sun, Yu Gu, Xiaohua Li, Ge Yu
Proceedings of SIGIR  ·  2025  ·  CCF-A
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
Shuliang Liu, Xinze Li, Zhenghao Liu, Yukun Yan, Cheng Yang, Zheni Zeng, Zhiyuan Liu, Maosong Sun, Ge Yu
Proceedings of ACL (Findings)  ·  2025  ·  CCF-A
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, , Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
Proceedings of ACL  ·  2025  ·  CCF-A
Rankcot: Refining knowledge for retrieval-augmented generation through ranking chain-of-thoughts
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
Proceedings of ACL  ·  2025  ·  CCF-A

最新动态

We have three papers accepted by ACL 2025

We have three papers accepted by ACL 2025: The 63rd Annual Meeting of the Association for Computational Linguistics

We have one paper accepted by SIGIR 2025

We have one paper accepted by SIGIR 2025: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval

We have three papers accepted by ICLR 2025

We have three papers accepted by ICLR 2025: The Thirteenth International Conference on Learning Representations

合作课程

OpenBMB × Hugging Face × THUNLP,联袂献上经典大模型课

这个夏天,THUNLP 携手 Hugging Face 和 OpenBMB,推出大模型公开课第二季。