Yue Huang | 黄跃
PhD Student of Computer and Science · University of Notre Dame
About Me
I’m a second-year PhD student in MINE Lab of Computer Science and Engineering (CSE) at the University of Notre Dame began from Fall 2024, supervised by Leonard C. Bettex Collegiate Prof. Xiangliang Zhang. I’m also a graduate student in Foundation Models and Applications Lab (FMAL) at Lucy Family Institute for Data & Society. I obtained my bachelor’s degree from Sichuan University in 2024. In 2025 summer, I worked with Prasanna Sattigeri and Pin-Yu Chen at MIT-IBM Watson AI Lab and IBM Research AI. Previously, I was a visiting student under the guidance of Prof. Lichao Sun. This experience was enhanced by mentorship from Prof. Philip S. Yu. Earlier before, I worked under Prof. Tang Jie and Dr. Xiao Liu at Tsinghua University.
- I welcome the opportunity to connect with colleagues in my field as well as those from interdisciplinary areas.
- My recent research centers on: (1) the science of foundation models, with a particular emphasis on their trustworthiness; (2) edge or tailed alignment of foundation models; (3) dynamic evaluation protocols tailored for generative models; and (4) challenging the capability boundary of frontier models (e.g., VAB).
- If you are interested in my research, please contact me via email or for an in-person conversation.
Research Interests
My research is centered on three pivotal questions:
News
Selected Publications
Disclaimer: This material is presented to ensure the timely dissemination of scholarly works. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms invoked by each author’s copyright.
*: Equal Contribution
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang
Findings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026 Findings)
TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
Yue Huang, Chujie Gao, Siyuan Wu, Haoran Wang, Xiangqi Wang, Jiayi Ye, Yujun Zhou, Yanbo Wang, et al.
The Fourteenth International Conference on Learning Representations (ICLR 2026)
(Featured by the Hoover Institution Technology Policy Accelerator and the Notre Dame-IBM Technology Ethics Lab)
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou, Pengcheng Jing, Manish Nagireddy, Inkit Padhi, Greta Dolcetti, Zhangchen Xu, Subhajit Chaudhury, Ambrish Rawat, Liubov Nedoshivina, Pin-Yu Chen, Prasanna Sattigeri, Xiangliang Zhang
The Fourteenth International Conference on Learning Representations (ICLR 2026)
SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
Yue Huang, Xiangqi Wang, Xiangliang Zhang
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026 Oral)
RMO: Towards Better LLM Alignment via Reshaping Reward Margin Distributions
Yanchi Ru*, Yue Huang*, Xiangliang Zhang
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)
Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement
Xiaonan Luo*, Yue Huang*, Ping He, Xiangliang Zhang
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)
ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions
Yue Huang*, Zhengzhe Jiang*, Xiaonan Luo, Kehan Guo, Haomin Zhuang, Yujun Zhou, Zhengqing Yuan, Xiaoqi Sun, Jules Schleinitz, Yanbo Wang, Shuhao Zhang, Mihir Surve, Nitesh V Chawla, Olaf Wiest, Xiangliang Zhang
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
(Highlighted in the semi-annual meeting hosted by NSF Center for Computer-Assisted Synthesis (C-CAS))
AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
Xiangqi Wang*, Yue Huang*, Yanbo Wang, Xiaonan Luo, Kehan Guo, Yujun Zhou, Xiangliang Zhang
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025 Spotlight)
Exposing and Patching the Flaws of Large Language Models in Social Character Simulation
Yue Huang*, Zhengqing Yuan*, Yujun Zhou, Kehan Guo, Xiangqi Wang, Haomin Zhuang, Weixiang Sun, Lichao Sun, Jindong Wang, Yanfang Ye, Xiangliang Zhang
Second Conference on Language Modeling (COLM 2025)
DataGen: Unified Synthetic Dataset Generation via Large Language Models
Yue Huang*, Siyuan Wu*, Chujie Gao, Dongping Chen, Qihui Zhang, Yao Wan, Tianyi Zhou, Chaowei Xiao, Jianfeng Gao, et al.
The Thirteenth International Conference on Learning Representations (ICLR 2025)
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
Jiayi Ye*, Yanbo Wang*, Yue Huang*, Dongping Chen, Qihui Zhang, Nuno Moniz, Tian Gao, Werner Geyer, Chao Huang, Pin-Yu Chen, Nitesh V Chawla, Xiangliang Zhang
The Thirteenth International Conference on Learning Representations (ICLR 2025)
(Highlighted by the Notre Dame-IBM Technology Ethics Lab, with a related tutorial video)
My Favorite Streamer is an LLM: Discovering, Bonding, and Co-Creating in AI VTuber Fandom
Jiayi Ye, Chaoran Chen, Yue Huang, Yanfang Ye, Toby Jia-Jun Li, Xiangliang Zhang
2026 CHI Conference on Human Factors in Computing Systems (ACM CHI 2026, Honourable Mention Award)
(Cited by Wikipedia and featured in a high-impact Bilibili video with 247K+ views, 10.6K likes, and 6.3K saves)
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.
2024 International Conference on Machine Learning (ICML 2024)
(Widely recognized by leading U.S. and international AI safety communities: highlighted by United States Department of Homeland Security (DHS) & International AI Safety Report; listed in the U.S. DoD CDAO Generative AI Responsible AI Toolkit; featured in NIST AI 100-2e2025; adopted as an official benchmark in all three editions of the FLI AI Safety Index to grade Anthropic, OpenAI, Google DeepMind, xAI, Meta, DeepSeek, Z.ai, and Alibaba Cloud; profiled by Lawrence Livermore National Laboratory (U.S. DOE/NNSA); chapter-length treatment in the Springer textbook Introduction to Foundation Models (2025, Ch. 12 "Trustworthiness Evaluation of Large Language Models"); supported by a Microsoft Accelerate Foundation Models Research Award; Invited Talk at IBM Research)
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
Yue Huang, Jiawen Shi, Yuan Li, Chenrui Fan, Siyuan Wu, Qihui Zhang, Yixin Liu, Pan Zhou, et al.
The Twelfth International Conference on Learning Representations (ICLR 2024)
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
Yue Huang*, Chenrui Fan*, Yuan Li, Siyuan Wu, et al.
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
HonestLLM: Toward an Honest and Helpful Large Language Model
Chujie Gao*, Siyuan Wu*, Yue Huang*, Dongping Chen*, Qihui Zhang*, et al.
Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
Talks & Guest Lecture
Recognition & Impact
- United States Department of Homeland Security (DHS). Highlighted TrustLLM: Trustworthiness in Large Language Models in this report.
- International AI Safety Report. Cited TrustLLM: Trustworthiness in Large Language Models in both the 2025 edition and the 2026 edition — with the 2026 report elevating it to a core empirical source supporting the report's central finding on "persistent deficiencies on measures of truthfulness, safety, and robustness" (p. 99).
- U.S. DoD CDAO Generative AI Responsible AI Toolkit. Listed TrustLLM: Trustworthiness in Large Language Models in the official toolkit.
- NIST AI 100-2e2025. Featured TrustLLM: Trustworthiness in Large Language Models in Section 3.6, "Benchmarks for AML Vulnerabilities" of the official report.
- FLI AI Safety Index. Adopted TrustLLM: Trustworthiness in Large Language Models as an official benchmark in all three editions: AI Safety Index 2024, AI Safety Index Summer 2025, and AI Safety Index Winter 2025.
- Lawrence Livermore National Laboratory (U.S. DOE/NNSA). Profiled TrustLLM: Trustworthiness in Large Language Models in Evaluating trust and safety of large language models.
- Springer textbook. Gave TrustLLM: Trustworthiness in Large Language Models chapter-length treatment in Introduction to Foundation Models (2025, Ch. 12).
- Hoover Institution Technology Policy Accelerator. Featured TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models in the Technology Policy Accelerator.
- Notre Dame-IBM Technology Ethics Lab. Selected TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models as a Collaborative Project.
- Notre Dame-IBM Technology Ethics Lab. Highlighted Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge in an official highlight.
- IBM tutorial video. Featured Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge in a dedicated tutorial video.
- Science. Reported on Benchmarking large language models on safety risks in scientific laboratories in Leading AI models miss dangerous lab risks.
- New Scientist. Highlighted Benchmarking large language models on safety risks in scientific laboratories in All major AI models risk encouraging dangerous science experiments.
Honors and Awards
Academic Participation
Educations
Present
Jun. 2024
Internships
Sep. 2026
Dec. 2025
Aug. 2025
Jan. 2024
Acknowledgment
I am honored that my research is funded, supported, or recognized by:
Misc
- I spent 18 years in my hometown, Fujian 🇨🇳, and had 4 wonderful years of university life in Sichuan 🌶️ (I can handle spicy food!).
- I love exchanging ideas with people from different fields 🌍 — it helps me see the world more broadly.
- My favorite singers are Eason Chan and Steve Chou;小剛 🎤. Lately, I've been listening to Patti Tsai.
- My favorite sports are swimming 🏊 and badminton 🏸. I also enjoy capturing scenic moments with my camera 📷.
- I'm deeply grateful to those who've helped me along the way 🙏 — thank you for helping me go further!