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 NeurIPS、ICLR、ACL、EMNLP、NAACL、SIGIR、KDD、WebConf、ICASSP 等国际国内顶级会议及期刊发表 70 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 5k 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

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
Yifan Ji, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Qian Zhang, Zhibo Yang, Junyang Lin, Yu Gu, Ge Yu, Maosong Sun
Proceedings of ACL  ·  2026CCF-A
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
Zhenghao Liu, Zhuoyang Wu, Xinze Li, Yukun Yan, Shuo Wang, Zulong Chen, Yu Gu, Ge Yu, Maosong Sun
Proceedings of ACL  ·  2026CCF-A
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
Proceedings of ACL  ·  2026CCF-A
Empirical Analysis of Decoding Biases in Masked Diffusion Models
Empirical Analysis of Decoding Biases in Masked Diffusion Models
Pengcheng Huang, Tianming Liu, Zhenghao Liu, Yukun Yan, Shuo Wang, Tong Xiao, Zulong Chen, Maosong Sun
Proceedings of ACL  ·  2026CCF-A

最新动态

We have 12 papers accepted by ACL 2026

We have 12 papers accepted by ACL 2026: The 64th Annual Meeting of the Association for Computational Linguistics

We have two papers accepted by SIGIR 2026

We have two papers accepted by SIGIR 2026: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval

We have two papers accepted by ICASSP 2026

We have two papers accepted by ICASSP 2026: The 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing

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。