Kai Shu   

Assistant Professor

Department of Computer Science

Emory University

Office: MSC N424

Mail: 400 Dowman Drive, Atlanta, GA 30322

E-mail: kai.shu at emory.edu
X: @KaiShu0327

Google Scholar

 

News and Highlights

[11/2024] Two papers are accepted in COLING 2025.

[11/2024] Invited to talk at Stanford University.

[9/2024] One paper is accepted in NeurIPS 2024.

[9/2024] Two papers are accepted in SIGKDD Explorations and EMNLP 2024.

[7/2024] Two papers are accepted in DSAA 2024.

[7/2024] One paper is accepted in CIKM 2024.

[6/2024] Received a NSF grant on open-source anomaly detection, joint with UIC, USC, and Lehigh.

[4/2024] Received the NSF CAREER Award on fairness AI in the real world! [IIT News]

[2/2024] Invited to participate the Cisco Research LLM Factuality Hallucination Summit.

[1/2024] Received the IIT College of Computing Dean's Excellence in Research Award.

[1/2024] One paper is accepted in ICLR 2024.

[11/2023] Received a DHS grant through CAOE to study combating misinformation in LLM era. [IIT News]

[10/2023] Received a Cisco Faculty Research Award to study large language models (LLMs).

[10/2023] Elevated to IEEE Senior Member.

[10/2023] One paper is accepted in EMNLP 2023 Findings.

[9/2023] Received the 2023 Microsoft Accelerate Foundation Models Research Award [Microsoft News].

[9/2023] One paper is accepted in ACM SIGSPATIAL 2023.

[8/2023] Received a DOE grant to study machine learning surrogate modeling for distributed system simulations.

[6/2023] Invited to serve as an Area Chair for NeurIPS 2023 Datasets and Benchmarks.

[6/2023] Invited to serve as a Senior PC for AAAI 2024.

[5/2023] Received the DARPA AI Forward Scholarship [Workshop Recap].

[5/2023] One paper is accepted in KDD 2023.

[5/2023] Invited to serve as the PC Vice-Chair for Bench'23.

[4/2023] Received an IARPA grant on interpretable authorship attribution and obfuscation [IIT News].

[4/2023] Two papers are accepted in ACM SIGSIM-PADS’23.

[3/2023] Keynote invitation in BeyondFacts 2023 workshop, collocated in TheWebConf'23

Kai Shu is an Assistant Professor in the Department of Computer Science at Emory University. His research lies in machine learning, data mining, social computing with applications such as disinformation, education, and healthcare. Prior to joining Emory in 2024, he was the Gladwin Development Chair Assistant Professor in Computer Science at Illinois Institute of Technology. He obtained his PhD in Computer Science at Arizona State University, under the supervision of Professor Huan Liu. He is the recipient of 2024 NSF CAREER Award, 2024 IIT College of Computing Dean's Excellence in Research Award, 2023 Microsoft Accelerate Foundation Models Research Award, 2023 DARPA AI Forward Scholarship Award, 2023 AAAI New Faculty Highlights, 2023/2022 Cisco Faculty Research Awards, the finalist of a 2022 Meta Research Award, and 2020 ASU Engineering Dean's Dissertation Award. He interned at Microsoft Research AI, Yahoo Research and HP Labs. His research is generously supported by federal agencies such as NSF, DARPA, IARPA, DHS, and DOE, as well as industrial collaborators such as Cisco, Google, and Microsoft.

I am ACTIVELY looking for Postdocs and multiple self-motivated PhD students to conduct research in the area of data mining, machine learning, social computing, and natural language processing. Interested students please feel free to drop me an email with your CV and transcript (I can not reply to every individual email).

Research Interests 

  • AI for Social Good: dis-/misinformation, privacy, security, healthcare.
  • Trustworthy AI: interpretability, robustness, fairness.
  • Learning with Imperfect Data: self-/weakly-supervised learning, meta learning, data augmentation.
  • Applied Machine Learning: text/graph mining, multimodal learning, adversarial learning.
  • Large Foundation Models: factuality, reliability, safety.

Detecting Fake News on Social Media
    Table of Contents
    Order Hard-cover or PDF
    Tools and Datasets
     		     Disinformation, Misinformation and Fake News in Social Media     Table of Contents
    An Introductory Chapter
    [A Chinese Introduction Blog][Vito]

Selected Publications [Full List]

  • Can Large Language Models Identify Authorship. [PDF]
    Baixiang Huang, Canyu Chen and Kai Shu
    Findings of The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024-Findings).
  • Backdoor Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment. [PDF]
    Haoran Wang, Kai Shu
    Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024).
  • Can LLM-Generated Misinformation Be Detected? [PDF]
    Canyu Chen, Kai Shu
    Proceedings of the 12th International Conference on Learning Representations (ICLR 2024).
  • Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models. [PDF]
    Haoran Wang, Kai Shu
    Findings of The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023-Findings).
  • MUSER : A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection. [PDF]
    Hao Liao, Jiahao Peng, Zhanyi Huang, Wei Zhang, Guanghua Li, Kai Shu, and Xing Xie.
    Proceedings of 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), ADS Track.
  • Attacking Fake News Detectors via Manipulating News Social Engagement. [PDF][A Blog on Montreal AI]
    Haoran Wang, Yingtong Dou, Canyu Chen, Lichao Sun, Philip S. Yu and Kai Shu.
    Proceedings of The 2023 ACM Web Conference (WWW 2023).
  • PromptDA: Label-guided Data Augmentation for Prompt-based Few Shot Learners. [PDF]
    Canyu Chen, Kai Shu.
    Proceedings of The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023).
  • A Model-Agnostic Approach to Differentially Private Topic Mining. [PDF]
    Han Wang*, Jayashree Sharma*, Shuya Feng, Kai Shu, and Yuan Hong.
    Proceedings of 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022)
  • WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding. [PDF][Code]
    Guoqing Zheng, Giannis Karamanolakis, Kai Shu, Ahmed Hassan Awadallah.
    Proceedings of 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)
  • "This is Fake! Shared it by Mistake": Assessing the Intent of Fake News Spreaders. [PDF]
    Xinyi Zhou, Kai Shu, Vir V. Phoha, Huan Liu and Reza Zafarani.
    Proceedings of The 2022 ACM Web Conference (WWW 2022)
  • Domain Adaptive Fake News Detection via Reinforcement Learning. [PDF]
    Ahmadreza Mosallanezhad, Mansooreh Karami, Kai Shu, Michelle Mancenido and Huan Liu.
    Proceedings of The 2022 ACM Web Conference (WWW 2022)
  • Causal Understanding of Fake News Dissemination on Social Media. [PDF]
    Lu Cheng, Ruocheng Guo, Kai Shu, and Huan Liu.
    Proceedings of 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021)
  • User Preference-aware Fake News Detection. [PDF][Code][PyG Example][DGL Example][Data][A video demo by DeepFindr]
    Yingtong Dou, Kai Shu, Congying Xia, Philip S. Yu, and Lichao Sun.
    Proceedings of 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021) (Short paper)
  • Fact-enhanced Synthetic News Generation. [PDF][Poster]
    Kai Shu*, Yichuan Li*, Kaize Ding, and Huan Liu.
    Proceedings of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021)
  • dEFEND: Explainable Fake News Detection. [PDF][Code]
    Kai Shu, Limeng Cui, Suhang Wang, Dongwon Lee, and Huan Liu.
    Proceedings of 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019)
    Media coverage: [Techxplore Today]
  • Fake News Detection on Social Media: A Data Mining Perspective. [PDF][Data]
    Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, and Huan Liu.
    SIGKDD Explorations, 2017.