Junchao Wu

Ph.D. Student in Computer Science

NLP2CT Lab, University of Macau

Email Twitter GitHub Google Scholar

About Me

I am Junchao Wu. I am a second-year Ph.D. student in Computer Science at NLP2CT Lab, University of Macau, fortunately advised by Prof. Derek F. Wong. Previously, I completed my M.S. in Data Science (Computational Linguistics) at the same lab, co-advised by Prof. Derek F. Wong and Prof. Yulin Yuan. I earned my bachelor's degree in Information Management and Information Systems at Beijing Normal University, Zhuhai. I am currently doing a research internship at Alibaba Cloud.

Research Overview

My core research centers on Trustworthy Large Language Models (explainable, controllable, and secure LLMs and their safety), with a primary focus on LLM-generated text detection and efficient model post-training.

• LLM-Generated Text Detection & Benchmarking: To address the opacity of AI-generated content, I released a systematic survey [CL'25] that highlights the field's key challenges and future directions. I then developed detection frameworks leveraging grammatical [COLING'25] and representation pattern [TACL'25] differences, constructed leading benchmarks tailored to multilingual and real-world scenarios [NeurIPS'24]; [ACL'26] and specialized domains (e.g., modern Chinese poetry [EMNLP'25]), and organized the shared task on this topic [NLPCC'25]; [NLPCC'26].
• Efficient and Controllable LLM Tuning & Reasoning: Focusing on efficient, controllable, and explainable LLM post-training and reasoning, I proposed a neuron-aware instruction tuning framework [ICLR'26]. Collaboratively, I investigated internal reasoning mechanisms of LLMs, including "aha moments" in complex problem-solving [TACL'26] and COT monitorability in LRMs [arXiv'25], to enhance model trustworthiness.
• Interpretability & Safety: I also work on LLM safety & ethics [ACL'25]; [EMNLP'25]; [ACL'26], covering debiasing optimization, resistance to fraud/phishing inducements, and political stance mitigation.
• Machine Translation and Multilingual: I engage in research on domain-adaptive machine translation [TALLIP'26] and the exploration of LLMs as evaluators [ICML2025@AIW 2025]; [ICML'26], as well as human-in-the-loop MT systems [MT Summit'23].

News

• 2026-05-01One paper accepted by ICML 2026 as Co-author: UniRRM.
• 2026-04-07Two papers accepted by ACL 2026 Main: DetectRL-X (First-author) and Political Stance Mitigation (Co-author).
• 2026-03-14One paper accepted by CVPR 2026 Findings as Co-author: LongDocSpan.
• 2026-01-27One paper accepted by ICLR 2026 as Co-first author: Neuron-Aware Data Selection for LLMs.
• 2026-01-05One paper accepted by ACM TALLIP as Co-author.
• 2025-08-21Two papers accepted by EMNLP 2025 Findings as Co-author. Our CL and TACL papers will also be presented orally at EMNLP 2025.
• 2025-08-01One paper accepted by TACL: RepreGuard (Co-first author).

Publications

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection

Junchao Wu, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu, Tianqi Shi, Yichao Du, Longyue Wang, Weihua Luo, Jinsong Su, Derek F. Wong†

ACL 2026 CCF-A

Paper Code

Neuron-Aware Data Selection in Instruction Tuning for Large Language Models

Xin Chen*, Junchao Wu* (Co-First), Shu Yang, Runzhe Zhan, Zeyu Wu, Min Yang, Shujian Huang, Lidia S. Chao, Derek F. Wong†

ICLR 2026 CCF-A

Paper Code

RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns

Xin Chen*, Junchao Wu* (Co-First), Shu Yang, Runzhe Zhan, Zeyu Wu, Ziyang Luo, Di Wang, Min Yang, Lidia S. Chao, Derek F. Wong†

TACL 2025 CCF-B SCI Q1

Paper Code

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

Junchao Wu, Runzhe Zhan, Derek F. Wong†, Shu Yang, Xinyi Yang, Yulin Yuan, Lidia S. Chao

NeurIPS 2024 CCF-A

Paper Code

A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions

Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan†, Derek F. Wong†, Lidia S. Chao

Computational Linguistics 2024 CCF-B SCI Q1

Paper Code

Oral Present in EMNLP 2025

UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms

Peng Lai, Yichao Du, Junchao Wu, Weibo Gao, Linan Yue, Longyue Wang, Weihua Luo, Derek F. Wong, Guanhua Chen†

ICML 2026 CCF-A

Paper Code

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di Wang†

ACL 2026 CCF-A

Paper Code

LongDocSpan: Extending LVLMs for Long Document Understanding

Junwei Liu, Xiong Wang, Junchao Wu, Yefeng Liu, Congyun Jin, Jiangwei Lao, Junjie Wang, Derek F. Wong, Zhihong Lu, Jian Wang, Ping Wang†

CVPR Findings 2026 CCF-A

Paper Code

Domain Adaptive Machine Translation with Synthetic Feedback for Large Language Models

Xinyi Yang, Runzhe Zhan, Junchao Wu, Yue Zhang, Xuebo Liu, Yujia Huo, Derek F. Wong†

ACM TALLIP 2026 CCF-C

Paper Code

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore

Junchao Wu, Runzhe Zhan, Derek F. Wong†, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang

COLING 2025 CCF-B

Paper Code

Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry

Shanshan Wang, Junchao Wu, Fengying Ye, Jingming Yao, Lidia S. Chao, Derek F. Wong†

EMNLP Findings 2025 CCF-B

Paper Code

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs

Shu Yang, Junchao Wu, Xuansheng Wu, Derek F. Wong, Ninhao Liu, Di Wang†

arXiv (Under Review) 2025

Paper Code

Why Do Metrics Think That? Towards Understanding Large Language Models as Machine Translation Evaluators

Runzhe Zhan, Xinyi Yang, Junchao Wu, Lidia S. Chao, Derek F. Wong†

ICML 2025 @ AIW 2025

Paper Code

Overview of CCL25-Eval Task 4: Factivity Inference Evaluation 2025

Guanliang Cong, Junchao Wu, Yang Chen, Tianqi Xun, Derek F. Wong, Bin Li, Yulin Yuan†

CCL 2025

Paper Code

Overview of the NLPCC 2025 Shared Task 1: LLM-Generated Text Detection

Junchao Wu, Runzhe Zhan, Qianli Wang, Yulin Yuan, Lidia S. Chao, Derek F. Wong†

NLPCC 2025 CCF-C

Paper Code

Understanding Aha Moments: From External Observations to Internal Mechanisms

Shu Yang, Junchao Wu, Xin Chen, Yunze Xiao, Xinyi Yang, Derek F. Wong, Di Wang†

arXiv (Under Review) 2025

Paper Code

Rethinking Prompt-based Debiasing in Large Language Models

Xinyi Yang, Runzhe Zhan, Derek F. Wong†, Shu Yang, Junchao Wu, Lidia S. Chao

ACL Findings 2025 CCF-A

Paper Code

Fraud-R1: A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang†

ACL Findings 2025 CCF-A

Paper Code

Human-in-the-loop Machine Translation with Large Language Model

Xinyi Yang, Runzhe Zhan, Derek F. Wong†, Junchao Wu, Lidia S. Chao

MT Summit 2023

Paper Code

The Canton Canon Digital Library Based on Knowledge Graph

Junchao Wu, Ying Jiang†, Xin Chen, Lingyu Guo, Xiaotong Wei, Xiaoyan Yang

ICEIT 2021

Paper Code

Best Oral Presentation Award (5/57)

Internships

LLM Research Intern Feb. 2026 – Present

Alibaba Cloud, Alibaba Group

Supervised by Yichao Du and Longyue Wang.

LLM Research Intern Jul. 2025 – Jan. 2026

Alibaba International, Alibaba Group

Supervised by Yefeng Liu and Longyue Wang.

Visiting Research Student Mar. 2025 – Jun. 2025

PRADA Lab, King Abdullah University of Science and Technology (KAUST)

Supervised by Prof. Di Wang.

Education

Ph.D. in Computer Science 2024 – Present

University of Macau

NLP2CT Lab, advised by Prof. Derek F. Wong.

M.S. in Data Science (Computational Linguistics) 2022 – 2024

University of Macau

NLP2CT Lab, co-advised by Prof. Derek F. Wong and Prof. Yulin Yuan.

B.S. in Computer Science 2018 – 2022

Beijing Normal University, Zhuhai

Professional Skills

Services

Others

Thanks to all the brilliant mentors, collaborators, and loved ones in my life.

• 🎓 Prof. Derek F. Wong and Prof. Yulin Yuan are my advisors at University of Macau. They are my guides — I am forever grateful for their quiet support and all the academic help they have given me.
• 💡 Runzhe Zhan is my mentor at NLP2CT Lab during my M.S. and Ph.D. He is a brilliant scientist and one of the nicest people I have ever met.
• 🏠 Yichao Du, Yefeng Liu, and Longyue Wang are my mentors during my internships at Alibaba Group. They are great seniors, brothers, and I am deeply grateful for their care and support.
• 🌈 Xin Chen is my undergraduate roommate and one of my best friends, who is presently a Ph.D. student at Nanjing University and is also committed to NLP research. He has many interesting dreams.
• 🤝 Guanhua Chen, Yutong Yao, and Shudong Liu are my Ph.D. fellows at NLP2CT Lab. We often discuss research over meals together — brothers forever in our hearts.
• ✨ Shu Yang and Xinyi Yang are my M.S. labmates and classmates in Computational Linguistics at University of Macau, now Ph.D. students at KAUST and Shenzhen University of Advanced Technology respectively. They are both hardworking, eager to learn, and full of academic talent. We have maintained great research collaborations.
• 🌟 Peng Lai is my colleague during my internship at Alibaba Group, a Ph.D. student at Southern University of Science and Technology. He is incredibly humble, highly capable, and a rising star in academia.
• ❤️ Qiufeng He, the love of my life and the best gift life has given me. A brilliant Assistant Professor in Engineering Management at Shenzhen University, and we dream to write the future of AI + Civil Engineering together. With her, everything matters, and everything awaits.