I am Dou Hu, an Assistant Professor at the Communication University of China (CUC). Before joining CUC, I received my Ph.D. degree from the University of Chinese Academy of Sciences (UCAS) and the Institute of Information Engineering, Chinese Academy of Sciences (IIE CAS) in 2025, advised by Prof. Songlin Hu.

My research interests include natural language processing and machine learning. My research goal is to develop more intelligent, efficient, and trustworthy AI systems for language understanding and generation. To achieve this, I currently focus on text representation learning to improve the generalization, robustness, and trustworthiness of language models, with a particular interest in representation learning theory and trustworthy large language models.

胡斗，中国传媒大学教师，研究方向是自然语言处理与机器学习，2025年6月博士毕业于中国科学院信息工程研究所和中国科学院大学。 近五年来，聚焦表示学习理论及其在社会媒体和大模型安全领域的应用，以第一或通讯作者身份在ACL、AAAI、EMNLP等国内外会议/期刊发表论文18篇（含第一作者14篇），包括CCF-A/清华A类论文13篇（含第一作者9篇），引用量达千余次。 曾获2025年中国中文信息学会”博士学位论文激励计划” (全国10名)、2023年Afrisenti-SemEval国际最佳系统奖（获奖比例<0.5%, 第一完成人）、2025年中国科学院院长特别奖（全院80名）、4项国际语义测评竞赛冠军（含第一完成人2项）等。 长期担任ACL、EMNLP、EACL等国际会议的领域主席。

Research Interests

• Machine Learning for NLP
  • Information-theoretic Representation Learning
  • Multi-task & Multi-objective Optimization
  • Probabilistic Methods & Causal Reasoning
• Trustworthy LLMs
  • Preference Optimization and Alignment
  • Ethics, Bias, and Fairness
  • LLM Content Moderation
• Social Media Analysis
  • Sentiment & Emotion Analysis
  • Harmful Content Detection

🔥 News

• May. 2026: 🎉 One paper was accepted at KDD 2026. Congrats to Lingwei Wei!
• Apr. 2026: 🎉 One paper was accepted at ACL 2026.
• Oct. 2025: 🎖 I was selected for the 2025 CIPS Doctoral Dissertation Incentive Program.
• Aug. 2025: 🎉 One paper was accepted at EMNLP 2025. Congrats to Haonan Sheng!
• Jun. 2025: 🎖 I received the CAS Presidential Scholarship - Special Prize.
• May. 2025: 🎉🎉 Two papers were accepted at ACL 2025.

📖 Selected Publications (Full List)

(# represents corresponding author)

2026

• Geometry-aware Test-Time Adaptation on Graphs.
  Lingwei Wei, Dou Hu#, Li Sun#, Chengze Li, Wei Zhou, Songlin Hu, Philip S. Yu. KDD 2026. (CCF-A)

• Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective.
  Dou Hu, Lingwei Wei, Hongjiang Xiao, Songlin Hu, Yuan Zhang. ACL 2026. (CCF-A)

2025

• Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation.
  Haonan Sheng, Dou Hu#, Lingwei Wei#, Wei Zhou, Songlin Hu. Findings of EMNLP 2025. (CCF-B Findings)
  [Paper]

• Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding.
  Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu. ACL 2025. (CCF-A)
  [Paper]

• An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding.
  Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu. AAAI 2025. (CCF-A)
  [Paper]

• Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection.
  Lingwei Wei, Dou Hu#, Wei Zhou, Philip S. Yu, Songlin Hu#. Findings of ACL 2025. (CCF-A Findings)
  [Paper]

2024

• Representation Learning with Conditional Information Flow Maximization.
  Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu. ACL 2024. (CCF-A)
  [Paper] [Code]

• Structured Probabilistic Coding.
  Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu. AAAI 2024. (CCF-A, Oral)
  [Paper] [Code]

• Multi-stream Information Fusion Framework for Emotional Support Conversation.
  Yinan Bao, Dou Hu, Lingwei Wei, Shuchong Wei, Wei Zhou, Songlin Hu. LREC-COLING 2024. (CCF-B)
  [Paper]

• Transferring Structure Knowledge: A New Task to Fake News Detection Towards Cold-Start Propagation.
  Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu. ICASSP 2024. (CCF-B)
  [Paper]

• Modeling the Uncertainty of Information Propagation for Rumor Detection: A Neuro-Fuzzy Approach.
  Lingwei Wei, Dou Hu, Wei Zhou, Xin Wang, Songlin Hu. TNNLS 2024. (CCF-B, SCI-Q1)
  [Paper]

2023

• Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations.
  Dou Hu, Yinan Bao, Lingwei Wei, Wei Zhou, Songlin Hu. ACL 2023. (CCF-A)
  [Paper] [Code]

• UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis.
  Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu. SemEval@ACL 2023. (1st Place, Best System Award)
  [Paper] [Code]

• Modeling Both Intra-and Inter-Modality Uncertainty for Multimodal Fake News Detection.
  Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu. TMM 2023. (CCF-B, SCI-Q1)
  [Paper]

2022

• MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations.
  Dou Hu, Xiaolong Hou, Lingwei Wei, Lianxin Jiang, Yang Mo. ICASSP 2022. (CCF-B)
  [Paper] [Code]

• VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding.
  Dou Hu, Xiaolong Hou, Xiyang Du, Mengyuan Zhou, Lianxin Jiang, Yang Mo, and Xiaofeng Shi. Findings of EMNLP 2022. (CCF-B Findings)
  [Paper]

• PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts.
  Mengyuan Zhou, Dou Hu, Mengfei Yuan, Meizhi Jin, Xiyang Du, Lianxin Jiang, Yang Mo, Xiaofeng Shi. SemEval@NAACL 2022. (1st Place)
  [Paper]

• PALI-NLP at SemEval-2022 Task 6: iSarcasmEval- Fine-tuning the Pre-trained Model for Detecting Intended Sarcasm.
  Xiyang Du, Dou Hu, Meizhi Jin, Lianxin Jiang, Xiaofeng Shi. SemEval@NAACL 2022. (1st Place)
  [Paper]

• PAIC at SemEval-2022 Task 5: Multi-Modal Misogynous Detection in MEMES with Multi-Task Learning and Multi-model Fusion.
  Meizhi Jin, Mengyuan Zhou, Mengfei Yuan, Dou Hu, Xiyang Du, Lianxin Jiang, Yang Mo, Xiaofeng Shi. SemEval@NAACL 2022. (2nd Place)
  [Paper]

• PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Transformers for Patronizing and Condescending Language Detection.
  Dou Hu, Zhou Mengyuan, Xiyang Du, Mengfei Yuan, Jin Zhi, Lianxin Jiang, Mo Yang, Xiaofeng Shi. SemEval@NAACL 2022. (1st Place)
  [Paper]

2021

• Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection.
  Lingwei Wei, Dou Hu, Wei Zhou, Zhaojuan Yue, Songlin Hu. ACL-IJCNLP 2021. (CCF-A, Oral)
  [Paper]

• DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations.
  Dou Hu, Lingwei Wei, Xiaoyong Huai. ACL-IJCNLP 2021. (CCF-A, Oral)
  [Paper] [Code]

• A Rumor Detection Approach based on Multi-relational Propagation Tree (一种基于多关系传播树的谣言检测方法).
  Dou Hu, Lingwei Wei, Wei Zhou, Xiaoyong Huai, Jizhong Han, Songlin Hu. Journal of Computer Research and Development 2021. (CCF-A Chinese)
  [Paper]

2020

• Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis.
  Lingwei Wei, Dou Hu#, Wei Zhou#, Xuehai Tang, Xiaodan Zhang, Xin Wang, Jizhong Han, Songlin Hu. ECML-PKDD 2020. (CCF-B)
  [Paper] [Code]

• SLK-NER: exploiting second-order lexicon knowledge for Chinese NER.
  Dou Hu, Lingwei Wei. SEKE 2020.
  [Paper] [Code]

🎖 Honors and Awards

• CIPS Doctoral Dissertation Incentive Program (中国中文信息学会”博士学位论文激励计划”), CIPS, 2025
• Beijing Outstanding Graduate, Beijing Municipal Commission of Education, 2025
• CAS Presidential Scholarship - Special Prize (中国科学院院长特别奖), CAS, 2025
• Best System Award, Afrisenti-SemEval 2023
• 1st Place, Sentiment Analysis for African Languages Task, SemEval 2023
• 1st Place, Patronizing and Condescending Language Detection Task, SemEval 2022
• 1st Place, Intended Sarcasm Detection Task, SemEval 2022
• 1st Place, Multimedia Automatic Misogyny Identification Task, SemEval 2022

💬 Invited Talks

• May 2025, Invited talk, “Information-theoretic Representation Learning and Its Applications in the AI Safety”, IIE, CAS.
• Apr. 2025, Invited talk, “Information-theoretic Representation Learning and Its Applications in the Media Field”, CUC.
• Jan. 2024, Paper presentation, “Structured Probabilistic Coding”, Youth Working Committee, CIPS.

📝 Academic Services

• Area Chair:
  • ACL 2025/2026, EMNLP 2025/2026, EACL 2025, ACL Rolling Review
• Conference Reviewer or Program Committee Member:
  • ICLR 2025/2026, AAAI 2025/2026, NeurIPS 2024, NAACL 2024, ACL 2023/2024, EMNLP 2023/2024
• Journal Reviewer:
  • Engineering Applications of Artificial Intelligence (EAAI)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Transactions on Mobile Computing (TMC)