个人简介

曹亚男，中国科学院信息工程研究所研究员，中国科学院大学岗位教授，博士生导师，信息内容分析研究室副主任，国家级青年人才，国家重点研发计划青年科学家项目首席；研究方向为自然语言处理、人工智能安全，目前聚焦大模型推理及可解释机制、大语言模型水印与溯源、可信智能体等；获PAKDD 2020最佳论文奖、WWW 2021最佳论文提名奖，2022年度中国电子学会科技进步二等奖；入选2018年度中国科学院青促会人才项目、2022年度中国科学院优秀导师、2023年度国科大朱李月华优秀教师、2023年度国科大领雁银奖、CCL 2023 新闻脉络检测评测任务第一名、NLPCC 2025 大模型生成文本检测任务第一名；在TPAMI、TKDE、TOIS、NeurIPS、ICML等CCF-A类会议和期刊上发表60余篇学术论文；担任FCS期刊青年编委、电子学报青年编委；ACL、COLING领域委员，AAAI、IJCAI高级程序委员会委员。主持国家重点研发计划青年科学家项目、中国科学院科技创新重点部署项目、国家自然科学基金联合基金课题在内的20余项国家级和国家部委科研项目。在国科大主讲《自然语言处理基础》、《自然语言处理实战》、《深度学习与自然语言处理》等课程，深受学生喜爱和好评。

招生理念

教育背景

• 2006-09—2012-07

  中国科学院计算技术研究所 · 智能信息处理实验室

  博士
• 2002-09—2006-07

  山东大学计算机科学与技术学院

  学士

教授课程

1. 自然语言处理实战
2. 自然语言处理基础
3. 深度学习与自然语言处理

获奖情况

1. 2018年度中国科学院青年创新促进会会员
2. 2020年度PAKDD最佳论文奖
3. 2021年度WWW最佳论文奖提名
4. 2022年度中国电子学会科学技术进步二等奖
5. 2022年度中国科学院优秀导师（院长特别奖指导教师）
6. 2023年度中国科学院大学朱李月华优秀教师
7. 2023年度中国科学院大学领雁银奖
8. CCL 2023 新闻脉络检测评测任务第一名
9. NLPCC 2025 大模型生成文本检测任务第一名

论文发表

• TOIS-2026 CCF-A Hong Zhou, Xixun Lin, Yanan Cao, Shichao Zhu, Renqi Jia, Xiangyu Zhao, Guandong Xu, Li Guo. D2TCDR: Disentangled Diffusion-Based Transfer for Cross-Domain Recommendation  [pdf]
• ACL-2026 CCF-A Lanxue Zhang, Yuqiang Xie, Fang Fang, Yubing Ren, Xuebin Wang, Yanan Cao. Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models  [pdf]
• ACL-2026 CCF-A Yongxuan Wu, Xixun Lin, He Zhang, Nan Sun, Kun Wang, Chuan Zhou, Shirui Pan, Yanan Cao. CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems  [pdf]
• ACL-2026 CCF-A Yixuan Nan, Xixun Lin, Yanmin Shang, Ge Zhang, Zheng Fang, Fang Fang, Yanan Cao. EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment  [pdf]
• ACL-2026 CCF-A Yilong Liu, Xixun Lin, Pengfei Cao, Ge Zhang, Fang Fang, Yanan Cao. Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations  [pdf]
• ACL-2026 CCF-A Xiaowei Zhu, Yubing Ren, Fang Fang, Shi Wang, Yanan Cao, Li Guo. Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection  [pdf]
• ACL-2026 CCF-A Hao Li, Yubing Ren, Yanan Cao, Yingjie Li, Fang Fang, Shi Wang, Li Guo. DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack  [pdf]
• ACL-2026 CCF-A Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang, Xiaoxue Li, Li Guo. Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework  [pdf]
• AAAI-2026 CCF-A Yu Liu, Xixun Lin, Yanmin Shang, Yangxi Li, Shi Wang, Yanan Cao. PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models. (Oral) [pdf]
• AAAI-2026 CCF-A Lanxue Zhang, Yuqiang Xie, Fang Fang, Fanglong Dong, Rui Liu, Yanan Cao. MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization.  [pdf]
• AAAI-2026 CCF-A Chuancheng Song, Hanyang Shen, Yan Dong, Xixun Lin, Yanmin Shang, Yanan Cao. Breaking One-size-fits-all: Revisiting Out-of-Distribution Detection on Graphs under Diverse Distribution Shifts.  [pdf]
• NeurIPS-2025 CCF-A Xiaowei Zhu, Yubing Ren, Fang Fang, Qingfeng Tan, Shi Wang, Yanan Cao. DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm. (Spotlight) [pdf]
• EMNLP-2025 CCF-B Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang, Shi Wang, Shirui Pan. Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning.  [pdf][code]
• ECAI-2025 CCF-B Yixuan Nan, Xixun Lin, Yanmin Shang, Zhuofan Li, Can Zhao, Yanan Cao. RANA: Robust Active Learning for Noisy Network Alignment.  [pdf][code]
• NLPCC-2025 CCF-C Zhuoshang Wang, Yubing Ren, Guoyu Zhao, Xiaowei Zhu, Hao Li, Yanan Cao. EnsemJudge: Enhancing Reliability in Chinese LLM-Generated Text Detection through Diverse Model Ensembles [pdf][code]
• ECML-2025 CCF-B Nan Sun, Xixun Lin*, Zhiheng Zhou, Yanmin Shang, Zhenlin Cheng, Yanan Cao. Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs.  [pdf]
• ACL-2025 CCF-A Yidan Wang, Yubing Ren, Yanan Cao, Binxing Fang. From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models.  [pdf]
• ACL-2025 CCF-A Yidan Wang, Yanan Cao, Yubing Ren, Fang Fang, Zheng Lin, Binxing Fang. PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization.  [pdf]
• ACL-2025 CCF-A Lanxue Zhang, Yanan Cao, Yuqiang Xie, Fang Fang, Yangxi Li. Dynamic Evaluation with Cognitive Reasoning for Multi-turn Safety of Large Language Models.  [pdf]
• ACL-2025 CCF-A Xiaowei Zhu, Yubing Ren, Yanan Cao, Xixun Lin, Fang Fang, Yangxi Li. Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction.  [pdf]
• KDD-2025 CCF-A Yongxuan Wu, Yang Liu, Xixun Lin, Hong Zhou, Yanan Cao, Lixin Zou, Yanmin Shang, Yanbing Liu. FairCDR: Transferring Fairness and User Preferences for Cross-Domain Recommendation.  [pdf]
• TOIS-2025 CCF-A Xixun Lin, Rui Liu, Yanan Cao, Lixin Zou, Qian Li, Yongxuan Wu, Yang Liu, Dawei Yin, Guandong Xu. Contrastive Modality-Disentangled Learning for Multimodal Recommendation.  [pdf]
• WWW-2025 CCF-A Hao Li, Yubing Ren, Yanan Cao, Yingjie Li, Fang Fang, Zheng Lin, Shi Wang. Bridging the Gap: Aligning Language Model Generation with Structured Information Extraction via Controllable State Transition. [pdf]
• WWW-2025 CCF-A Xixun Lin, Yanan Cao, Nan Sun, Lixin Zou, Chuan Zhou, Peng Zhang, Shuai Zhang, Ge Zhang, Jia Wu. Conformal Graph-level Out-of-distribution Detection with Adaptive Data Augmentation. [pdf]
• AAAI-2025 CCF-A Chuancheng Song, Xixun Lin, Hanyang Shen, Yanmin Shang, Yanan Cao. UniFORM: Towards Unified Framework for Anomaly Detection on Graphs. (Oral) [pdf]
• WWWJ-2024 CCF-B Yanan Cao, Xixun Lin, Yongxuan Wu, Fengzhao Shi, Yanmin Shang, Qingfeng Tan, Chuan Zhou, Peng Zhang. A Data-centric Framework of Improving Graph Neural Networks for Knowledge Graph Embedding. [pdf][code]
• WWWJ-2024 CCF-B Fengzhao Shi, Yanan Cao, Ren Li, Xixun Lin, Yanmin Shang, Chuan Zhou, Jia Wu, Shirui Pan. VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily. [pdf][code]
• ICML-2024 CCF-A Xixun Lin, Wenxiao Zhang, Fengzhao Shi, Chuan Zhou, Lixin Zou, Xiangyu Zhao, Dawei Yin, Shirui Pan, Yanan Cao. Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification. [pdf]
• ACL-2024 CCF-A Yubing Ren, Ping Guo, Yanan Cao, Wei Ma. Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models. [pdf][code]
• NAACL-2024 CCF-B Yanhe Fu, Yanan Cao∗, Qingyue Wang,and Yi Liu. TISE: A Tripartite In-context Selection Method for Event Argument Extraction. [pdf][code]
• WSDM-2024 CCF-B Yu Liu, Yanan Cao, Shi Wang, Qingyue Wang, Guanqun Bi. Generative Models for Complex Logical Reasoning over Knowledge Graphs.  [pdf][code]
• COLING-2024 CCF-B Yubing Ren, Yanan Cao, Hao Li, Yingjie Li, Zixuan Ma, Fang Fang, Ping Guo and Wei Ma. DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset. [pdf][code]
• ICASSP-2024 CCF-B Hao Li, Yanan Cao, Yubing Ren, Fang Fang, Lanxue Zhang, Yingjie Li, Shi Wang. Sorting, Reasoning, and Extraction: an Easy-to-Hard Reasoning Framework for Document-level Event Argument Extraction. [pdf][code]
• EMNLP-2023 CCF-B Hao Li, Yanan Cao, Yubing Ren, Fang Fang, Lanxue Zhang, Yingjie Li, Shi Wang. Intra-Event and Inter-Event Dependency-Aware Graph Network for Event Argument Extraction. [pdf]
• NLPCC-2023 CCF-C Yanhe Fu, Yi Liu, Yanan Cao, Yubing Ren, Qingyue Wang, Fang Fang, Cong Cao. A Multi-granularity Similarity Enhanced Model for Implicit Event Argument Extraction. [pdf][code]
• ACL-2023 CCF-A Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Denvy Deng, Qi Zhang. Towards Better Entity Linking with Multi-View enhanced Distillation. [pdf][code]
• ACL-2023 CCF-A Yubing Ren, Yanan Cao, Ping Guo, Fang Fang, Wei Ma, Zheng Lin. Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval Augmentation. [pdf]
• ACL-2023 CCF-A Guanqun Bi, Lei Shen, Yanan Cao, Meng Chen, Yuqiang Xie, Zheng Lin, Xiaodong He. DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation. [pdf][code]
• ACL-2023 CCF-A Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan, Zheng Lin, Shi Wang, Dacheng Tao, Li Guo. Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking. [pdf][code]
• WWW-2023 CCF-A Yuchen Zhou, Yanan Cao, Yongchao Liu, Yanmin Shang, Peng Zhang, Zheng Lin, Yun Yue, Baokun Wang, Xing Fu, Weiqiang Wang. Multi-Aspect Heterogeneous Graph Augmentation. [pdf][code]
• TOIS-2023 CCF-A Yuchen Zhou, Yanan Cao, Yanmin Shang, Chuan Zhou, Shirui Pan, Zheng Lin, Qian Li. Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation. [pdf][code]
• ACL-2022 CCF-A Ruipeng Jia, Xingxing Zhang, Yanan Cao*, Shi Wang, Zheng Lin, Furu Wei. Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization. [pdf][code]
• WWW-2022 CCF-A Fengzhao Shi, Yanan Cao, Yanmin Shang*, Yuchen Zhou, Chuan Zhou, Jia Wu. H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections. [pdf][code]
• AAAI-2022 CCF-A Ren Li, Yanan Cao, Qiannan Zhu, Guanqun Bi, Fang Fang*, Yi Liu, Qian Li. How Does Knowledge Graph Embedding Extrapolate to Unseen Data: a Semantic Evidence View. [pdf][code]
• ICDM-2022 CCF-B Yuchen Zhou, Yanan Cao, Yanmin Shang, Chuan Zhou, Chuancheng Song, Fengzhao Shi, Qian Li. Task-level Relations Modelling for Graph Meta-learning.  [pdf][code]
• WWWJ-2022 CCF-B Yuchen Zhou, Yanmin Shang, Yanan Cao, Qian Li, Chuan Zhou, Guandong Xu. API-GNN: Attribute Preserving Oriented Interactive Graph Neural Network. [pdf]
• COLING-2022 CCF-B Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu. CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction.  [pdf]
• COLING-2022 CCF-B Qingyue Wang, Yanan Cao, Piji Li and Li Guo. Slot Dependency Modeling for Zero-shot Cross-domain Dialogue State Tracking.  [pdf]
• IJCNN-2021 CCF-C Qingyue Wang, Yanan Cao, Junyan Jiang, Yafang Wang and Li Guo. Incorporating Specific Knowledge into End-to-End Task-oriented Dialogue Systems. [pdf]
• AAAI-2021 CCF-A Ruipeng Jia, Yanan Cao*, Haichao Shi, Fang Fang, Pengfei Yin, Shi Wang. Flexible Non-Autoregressive Extractive Summarization with Threshold: How to Extract a Non-Fixed Number of Summary Sentences? [pdf][code]
• ACL-2021 CCF-A Ruipeng Jia, Yanan Cao*, Fang Fang, Yuchen Zhou, Zheng Fang, Yanbing Liu, Shi Wang. Deep Differential Amplifier for Extractive Summarization. [pdf][code]
• ICASSP-2021 CCF-B Hengzhu Tang, Yanan Cao*, Zhenyu Zhang, Ruipeng Jia, Fang Fang, Shi Wang. Multi-Granularity Hetegrogeneous Graph For Document-level Relation Extraction.
• EMNLP-2021 CCF-B Zheng Fang, Yanan Cao, Tai Li, Ruipeng Jia, Fang Fang, Yanmin Shang, Yuhai Lu. TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network.
• WWWJ-2021 CCF-B Xiaoxue Li, Yanan Cao*, Yanmin Shang, Yangxi Li, Qian Li, Guandong Xu. RLINK: Deep Reinforcement Learning for User Identity Linkage.  [pdf]
• EMNLP-2020 CCF-B Ruipeng Jia, Yanan Cao*, Hengzhu Tang, Fang Fang, Cong Cao, Shi Wang. Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network. [pdf][code]
• CIKM-2020 CCF-B Ruipeng Jia, Yanan Cao*, Haichao Shi, Fang Fang, Yanbing Liu, Jianlong Tan. DistilSum: Distilling the Knowledge for Extractive Summarization. [pdf][code]
• WWW-2020 CCF-A Zheng Fang, Yanan Cao*, Ren Li, Zhenyu Zhang, Yanbing Liu, Shi Wang. High quality Candidate Generation and Sequential Graph Attention Network for Entity Linking. [pdf][code]
• AAAI-2020 CCF-A Xiaoxue Li, Yanan Cao*, Yanmin Shang, Yangxi Li, Yanbing Liu, Jianlong Tan. Type-aware Anchor Link Prediction across Heterogeneous Networks based on Graph Attention Network. [pdf]
• WWW-2019 CCF-A Zheng Fang, Yanan Cao*, Qian Li, Dongjie Zhang, Zhenyu Zhang, Yanbing Liu. Joint Entity Linking with Deep Reinforcement Learning.  [code]
• ICME-2019 CCF-B Yanmin Shang, Zhezhou Kang, Yanan Cao*, Yanbing Liu, Jianlong Tan. PAAE: A Unified Framework for Predicting Anchor Links with Adversarial Embedding.
• PAKDD-2020 CCF-C Hengzhu Tang, Yanan Cao, Zhenyu Zhang, Jiangxia Cao, Fang Fang, Shi Wang, Pengfei Yin. HIN: Hierarchical Inference Network for Document-Level Relation Extraction. (Best Paper Award)
• KSEM-2018 CCF-C Qingyue Wang, Yanjing Song, Hao Liu, Yanan Cao and Li Guo. A Sequence Transformation Model for Chinese Named Entity Recognition.  [pdf]

Undertaking Research Projects