About
I am a Ph.D. student in Computer Science at the University of Illinois Chicago (UIC), advised by Dr. Lu Cheng.
Prior to this, I obtained my Master's degree from the Shanghai Advanced Research Institute, University of Chinese Academy of Sciences (UCAS), under the supervision of Prof. Jun Huang, and my Bachelor's degree from Soochow University.
My research interests focus on two areas: Trustworthy LLMs, Agents & Post-Training (agent skill and security, LLM safety alignment, and RL post-training) and Graph Learning & Foundation Models for LLMs (graph learning, foundation models, and their connection to LLMs and agents).
Trustworthy AI
LLM Safety & Alignment
LLM Agents
RL Post-Training
Graph Foundation Models
Graph Learning
Research Projects
Trustworthy LLMs, Agents & Post-Training
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
Co-first author · ACM SIGKDD 2026
Designed a personalized safety-alignment framework for LLM conversational recommenders that enforces user-specific safety constraints while preserving recommendation quality.
POISE: Position-Aware Undetectable Skill Injection on LLM Agents
Co-first author (lead) · EMNLP 2026 (under review)
Designed a stealthy skill-poisoning attack that hides a single benign-looking trigger in a skill file, reaching 90–97% trigger rates on the Skill-Inject benchmark while evading the agent’s inspection.
CorVer: Lightweight Corpus-Grounded Process Rewards for Factual QA
Co-author (equal contribution) · EMNLP 2026 (under review)
Co-developed a plug-in process reward for RL on knowledge-intensive QA that replaces expensive neural verifiers with a corpus-grounded signal from Wikipedia co-occurrence statistics.
Graph Learning & Foundation Models for LLMs
Graph Representation Learning on Heterogeneous Information Networks
First author · ESWA 2026; NCA 2025
Designed progressive alternating attribute-structure optimization for multiplex heterogeneous graphs, improving robustness under missing attributes and noisy edges (ESWA 2026); developed a multi-level semantics extraction method for node classification (NCA 2025).
Technical Skills
LLM & Agents: LLM evaluation, LLM-as-a-Judge, agent skill, safety alignment, RL post-training, LLM training & inference (HuggingFace, vLLM, Unsloth, TRL), agent systems (Claude Code, Codex, OpenClaw)
Graph & ML: PyTorch, graph neural networks, graph foundation models, uncertainty quantification, conformal prediction, meta-learning, domain adaptation
Programming & Tools: Python, Java, SQL, Git, Docker, Daytona, Linux, LaTeX, TensorBoard, databases (SQL, MongoDB)
Education
Ph.D. in Computer Science
University of Illinois Chicago (UIC), Chicago, IL, USA
Aug. 2025 – Present | Advisor: Dr. Lu Cheng
M.Eng. in Electronic & Information Engineering
Shanghai Advanced Research Institute, University of Chinese Academy of Sciences, Shanghai, China
Sept. 2022 – June 2025 | Advisor: Prof. Jun Huang
B.Eng. in Computer Science & Technology
Soochow University, Suzhou, China
Sept. 2018 – June 2022
Publications
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
H. Hao, Y. Xu, X. Li, Y. Ge, L. Cheng
Accepted at ACM SIGKDD 2026, Research Track | arXiv:2603.03536 (2026)
POISE: Position-Aware Undetectable Skill Injection on LLM Agents
H. Hao, D. Min, Z. Zhang, Y. Zhang, M. Xu, Y. Ge, L. Cheng
Under review at EMNLP 2026 | arXiv:2606.07943 (2026)
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
S. Fan, H. Hao, D. Min, W. Liu, P. S. Yu, L. Cheng
Under review at EMNLP 2026 | arXiv:2605.29648 (2026)
Progressive Alternating Attribute-Structure Optimization for Multiplex Heterogeneous Graphs
H. Hao, J. Huang, S. Rao
Expert Systems with Applications, 312, 131495 (2026)
Heterogeneous Graph Multi-level Semantics Extraction for Node Classification
H. Hao, J. Huang, S. Rao
Neural Computing & Applications, 37, 11821–11841 (2025)
Invention Patents
J. Huang & H. Hao. “Node Classification Method, Device, Terminal, and Medium Based on Multi-level Semantic Representation of Heterogeneous Knowledge Graphs.” Approved.
Awards & Honors
Multiple “Three Good Student” awards at the University of Chinese Academy of Sciences and Soochow University for outstanding academic and overall performance.
