I am currently a first-year PhD student in Manning College of Information & Computer Sciences, University of Massachusetts Amherst, fortunately advised by Prof. Andrew Lan.
Before that, I was an algorithm engineer at TAL Education Group (NYSE: TAL) and gratefully supervised by Prof. Zitao Liu.
Prior to TAL, I got my M.S. degree in the NLP2CT Lab at the University of Macau, thankfully advised by Prof. Derek F. Wong.
My research interests lie in the field of AI in Education and Natural Language Processing. More specifically, I am exploring the following topics:
- Knowledge Tracing (KT): benchmarking of deep learning-based KT models, scalable architectures, interpretable and robust student modeling;
- Large Language Models (LLMs) for Education: instructional content generation using multi-agent frameworks, SFT and RAG paradigms;
- Dialogue Analysis: assessing student performance through LLM reasoning over tutor-student dialogues.
Additionally, I am one of the main developers of pyKT (GitHub 300+ ⭐ and 50k+ 📥).
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Honors & Awards
-
🏆 Top 100 Open Source Achievement Award2023
-
🥇 First Prize, The Quest for Quality Questions2023
-
🌟 Best Paper Honorable Mention (Resource Track), CIKM2022
Services
-
PC Member of WWW2026, 2024
-
PC Member of AAAI2026
-
PC Member of SIGIR2025
-
PC Member of AIED2025, 2024, 2023
News
Selected Publications (view all )
Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
Shuyan Huang, Alexander Scarlatos, Jaewook Lee, Andrew Lan
21st BEA workshop at ACL 2026
An interpretable difficulty-aware conversational KT framework built upon LLMs, which explicitly models students' abilities and the difficulties of tutor-posed tasks turn by turn.
Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
Shuyan Huang, Alexander Scarlatos, Jaewook Lee, Andrew Lan
21st BEA workshop at ACL 2026
An interpretable difficulty-aware conversational KT framework built upon LLMs, which explicitly models students' abilities and the difficulties of tutor-posed tasks turn by turn.
Knowledge-enhanced large language models for automatic lesson plan generation
Ying Zheng*, Shuyan Huang*, Xiaoli Zeng, Yaying Huang, Zitao Liu, Weiqi Luo (* equal contribution)
Nature Humanities and Social Sciences Communications 2025
Enhancing large language models with educational domain knowledge to improve the accuracy of generated lesson plans.
Knowledge-enhanced large language models for automatic lesson plan generation
Ying Zheng*, Shuyan Huang*, Xiaoli Zeng, Yaying Huang, Zitao Liu, Weiqi Luo (* equal contribution)
Nature Humanities and Social Sciences Communications 2025
Enhancing large language models with educational domain knowledge to improve the accuracy of generated lesson plans.
Dual-attentional time-aware fusion networks for knowledge tracing
Shuyan Huang, Zitao Liu, Qiongqiong Liu, Jiahao Chen, Yaying Huang
Information Fusion 2025
A dual-attentional time-aware fusion network for knowledge tracing that captures both temporal dynamics and question-level dependencies.
Dual-attentional time-aware fusion networks for knowledge tracing
Shuyan Huang, Zitao Liu, Qiongqiong Liu, Jiahao Chen, Yaying Huang
Information Fusion 2025
A dual-attentional time-aware fusion network for knowledge tracing that captures both temporal dynamics and question-level dependencies.
Enhancing deep knowledge tracing with auxiliary tasks
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang, Boyu Gao, Weiqi Luo, Jian Weng
The Web Conference (WWW) 2023
Boosting knowledge tracing performance through the integration of multi-task learning with auxiliary educational objectives.
Enhancing deep knowledge tracing with auxiliary tasks
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang, Boyu Gao, Weiqi Luo, Jian Weng
The Web Conference (WWW) 2023
Boosting knowledge tracing performance through the integration of multi-task learning with auxiliary educational objectives.
simpleKT: a simple but tough-to-beat baseline for knowledge tracing
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang#, Weiqi Luo (# corresponding author)
ICLR 2023
A surprisingly effective and simple baseline for knowledge tracing that consistently outperforms complex deep learning models.
simpleKT: a simple but tough-to-beat baseline for knowledge tracing
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang#, Weiqi Luo (# corresponding author)
ICLR 2023
A surprisingly effective and simple baseline for knowledge tracing that consistently outperforms complex deep learning models.
Improving interpretability of deep sequential knowledge tracing models with question-centric cognitive representations
Jiahao Chen, Zitao Liu, Shuyan Huang, Qiongqiong Liu, Weiqi Luo
AAAI 2023
Improving the interpretability of deep knowledge tracing by learning question-centric cognitive representations.
Improving interpretability of deep sequential knowledge tracing models with question-centric cognitive representations
Jiahao Chen, Zitao Liu, Shuyan Huang, Qiongqiong Liu, Weiqi Luo
AAAI 2023
Improving the interpretability of deep knowledge tracing by learning question-centric cognitive representations.
pyKT: a python library to benchmark deep learning based knowledge tracing models
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang#, Jiliang Tang, Weiqi Luo (# corresponding author)
NeurIPS 2022
A comprehensive Python library designed to provide a standardized benchmark for deep learning-based knowledge tracing.
pyKT: a python library to benchmark deep learning based knowledge tracing models
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang#, Jiliang Tang, Weiqi Luo (# corresponding author)
NeurIPS 2022
A comprehensive Python library designed to provide a standardized benchmark for deep learning-based knowledge tracing.