AP Humanities Scoring
AP 人文自动评分Automated scoring for AP history, literature & foreign-language writing — accurate, transparent, and equitable.
Academic Work
学术成果 · Academic Work
Publications, conference talks, and academic honors. Highlight markers in the author lists denote me.
01
Publications
论文列表Complete publication record across peer-reviewed venues and arXiv preprints.
2024
Investigating Generative AI Models and Detection Techniques: Impacts of Tokenization and Dataset Size on Identification of AI-Generated Text
Haowei Hua, Jiayu Yao
Frontiers in Artificial IntelligenceSpecial Section: NLP
Paper · DOI10.3389/frai.2024.1469197
Comparative Analysis of Machine Learning and Large Language Model Approaches for Detecting ChatGPT-Written Essays Under Revision Conditions
Haowei Hua, Jiayu Yao
IMPS 2024 Proceedings89th Annual Meeting, Prague
Paper · DOI10.64028/gnul779674
2025
Comparison of Scoring Rationales Between Large Language Models and Human Raters
Haowei Hua, Hong Jiao, Dan Song
arXiv 2025 · Preprint
Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays
Haowei Hua, Hong Jiao, Xinyi Wang
arXiv 2025 · Preprint
Exploring the Utilities of the Rationales from Large Language Models to Enhance Automated Essay Scoring
Hong Jiao, Hanna Choi, Haowei Hua
arXiv 2025 · Preprint
2026
Cost-efficient Generative AI Summarization for Scalable Automated Essay Scoring in Educational Assessment
Haowei Hua
arXiv 2026 · Preprint
02
Selected Projects
精选项目AI-Text Detection
AI 文本检测Tokenization & dataset-size effects on identifying AI-generated text — Frontiers in AI 2024 & IMPS 2024.
LLM Scoring Rationales
LLM 评分理由Comparing scoring rationales between large language models and human raters — arXiv 2025.
LLM Summarization for Essay Scoring
生成式摘要评分Cost-efficient generative-AI summarization for scalable automated essay scoring — arXiv 2026.
Genomic Sequence Modeling
基因组序列建模Deep-learning pipelines for genomic sequence modeling and molecular phenotype prediction — Westlake.
Social Media Behavior Analysis
社交媒体行为分析Multimodal machine learning on human behavior and communication in online discourse — Princeton.
03
Talks & Presentations
学术报告IMPS 2023 — College Park, MD · Co-author & Co-presenter
Features for Detecting Essays Produced by Generative AI — with Hong Jiao, C. Yadav, and L. Wan. Research on identifying features useful for detecting essays generated by emerging generative-AI systems. International Meeting of the Psychometric Society, July 24–28, 2023 · Conference Abstracts p. 217.
IMPS 2024 — Prague, Czech Republic · First Author & Presenter
Exploring Classic Machine Learning Models and Large Language Models in Detecting Chat-GPT Generated Essays in Writing Assessments — with Jiayu Yao. Comparative evaluation of classical ML and LLM approaches, including how human rewriting, AI rewriting, and grammar-based revisions affect detection. 89th International Meeting of the Psychometric Society, July 15–19, 2024.
NCME 2025 — Denver, CO · Second Author & Presenter · eBoard
Evaluation of the Performance for Automated Essay Scoring in Long Context — with K. Wang, Hong Jiao, and Dan Song. Approaches to scoring long-form essays and the limitations of conventional language-model architectures on extended text. National Council on Measurement in Education Annual Meeting, April 23–26, 2025.
IMPS 2025 · First Author
Scoring Rationale Comparison between Large Language Models and Human Raters: Insights from Automated Scoring Systems — with Hong Jiao (University of Maryland) and Dan Song (University of Iowa). Examined how LLM-generated scoring rationales compare with human raters’, with implications for interpretability and reliability of AI-assisted automated scoring. International Meeting of the Psychometric Society, 2025.
NCME AIME 2025 — Pittsburgh, PA · First Author & Presenter
Exploration of Summarization by Generative Language Models to Enhance Automated Scoring of Long Essays — with Hong Jiao (University of Maryland) and Xinyi Wang (University of Maryland / Beijing Normal University). A generative-AI approach to long-form essay scoring using LLM summarization to address input-length limits of transformer models. October 29, 2025.
04
Academic Honors & Awards
荣誉奖项Silver Medal — RSNA 2024 Lumbar Spine Degenerative Classification, Kaggle
International data-science competition focused on machine-learning methods for medical imaging and lumbar spine degeneration classification.
Gold Rank — USA Computing Olympiad (USACO)
Achieved Gold-level ranking in the United States of America Computing Olympiad.
State First Place & International Participant — Future Problem Solving Program
Earned first place at the state level and advanced to international-level competition.
Senior Division Award — Notre Dame Psychology
Received the Senior Division Award for work in psychology.
Culver Achievement Medal
Awarded in recognition of exceptional leadership and administrative performance, including service in senior cadet leadership and unit administrative roles.
Datasets & CodePlaceholder
Reproducible code and datasets for the essay-scoring and AI-detection projects will be linked here as they are released.
All placeholder slots above are ready for content — contact the site owner to fill them in.