I am a 4th-year Ph.D. candidate at Emory University advised by Dr. Kai Shu. I obtained my M.S. degree in computer science from University of Oregon in 2021 (advised by Dr. Thien Nguyen), and my B.S. degree in computer science from Purdue University in 2019 (working with Dr. Yung-Hsiang Lu). Previously, I worked as an applied scientist intern at Amazon AGI, Summer 2025.

💡 Research Interests

My research involves building trustworthy AI systems, with a specific emphasis on enhancing both robustness and interpretability. I am broadly interested in fundamental research and interdisciplinary collaborations motivated by important applications, including detecting misinformation and analyzing social network.

🔥 News

  • 2025.08:  🎉🎉 Completed my internship as an Applied Scientist at Amazon AGI!
  • 2025.07:  🎉🎉 Invited to serve as Program Committee member for AAAI 2026.
  • 2025.05:  🎉🎉 Excited to join Amazon AGI as an Applied Scientist Intern for Summer 2025 in Bellevue, WA.
  • 2025.05:  🎉🎉 Invited to serve as Area Chair for the NeurIPS Position Track.
  • 2025.02:  🎉🎉 Research Access Program has been awarded. Thanks OpenAI!
  • More
    • 2025.01: Fin-Fact has been accepted by WWW 2025. Congratulations Aman!
    • 2024.12: Invited as PC for ICML 2025 Position Track.
    • 2024.11: MMCV has been accepted by COLING 2025.
    • 2024.08: Our Fin-Fact dataset has been used for shared task for FinNLP@COLING2025
    • 2024.07: TA2 has been accepted by CIKM 2024.
    • 2024.05: TrustLLM has been accepted by ICML 2024. Congratulations Yue!
    • 2024.02: Passed Ph.D. Qualifying Exam.
    • 2023.10: FOLK has been accepted by EMNLP 2023.
    • 2023.02: MARL has been accepted by WWW 2023.

📜 Selected Publications

COLING 2025
sym

Piecing It All Together: Verifying Multi-Hop Multimodal Claims

Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu

Proceedings of the 31st International Conference on Computational Linguistics

git Leaderboard

CIKM 2024
sym

Trojan Activation Attack: Red-Teaming Large Language Models using Steering Vectors for Safety-Alignment

Haoran Wang, Kai Shu

Proceedings of the 33rd ACM International Conference on Information and Knowledge Management

git

ICML 2024
sym

TrustLLM: Trustworthiness in Large Language Models

Yue Huang*, Lichao Sun*, Haoran Wang*, Siyuan Wu*, Qihui Zhang*, Chujie Gao*, Yixin Huang*, Wenhan Lyu*, Yixuan Zhang*, Xiner Li*, Zhengliang Liu*, Yixin Liu*, Yijue Wang*, Zhikun Zhang*, Bhavya Kailkhura, Caiming Xiong, et al. (*: major contribution).

Proceedings of the Forty-first International Conference on Machine Learning

git hf Website Dataset Leaderboard Toolkit Document Downloads Metioned

EMNLP 2023
sym

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models

Haoran Wang, Kai Shu

Findings of the Association for Computational Linguistics: EMNLP 2023

git appear cisco

WWW 2023
sym

Attacking Fake News Detectors via Manipulating News Social Engagement

Haoran Wang, Yingtong Dou, Canyu Chen, Lichao Sun, Philip S. Yu, Kai Shu

Proceedings of the ACM Web Conference 2023

git video report

🔬 Research Experience

Emory University, Jan, 2025 – Present
Research Assistant

Amazon AGI, May, 2025 – Aug, 2025
Applied Scientist Intern

Illinois Institute of Technology, Aug, 2022 – Jan, 2025
Research Assistant

Purdue University, Aug, 2018 – May, 2019
Research Assistant

Education

  • 2022 - Now, Ph.D., Computer Science. Emory University.
  • 2021, M.S., Computer Science. University of Oregon.
  • 2019, B.S., Computer Science. Purdue University.

Academic Service

  • Area Chair: NeurIPS 2025 Position Track
  • Session Chair: CIKM 2024
  • Reviewer/Program Committee: KDD{2024, 2025}, AAAI{2024, 2025, 2026}, PAKDD{2025, 2026}, NeurIPS {2025}, ICML {2025}, ACML {2025}
  • Volunteer: ACM FAccT 2023

Last updated on Aug 16, 2025.