About Me

Hi! I am Beizhe Hu (胡焙哲), a PhD candidate under the supervision of Prof. Juan Cao at the Institute of Computing Technology, Chinese Academy of Sciences.

My research focuses on reliable information systems in the era of large language models. I am especially interested in:

  • Fake news and misinformation detection, and fact-checking
  • Natural language understanding and data mining
  • AI safety and AI for safety

I received my B.E. in Software Engineering from Xidian University in 2021.

I am currently on the job market, seeking opportunities in both academia and industry, and always open to collaborations. Feel free to get in touch by email.

Education

PhD in Computer Science and Technology (Candidate)
University of Chinese Academy of Sciences
Cultivation Unit: Institute of Computing Technology, Chinese Academy of Sciences
2021-now
B.E. in Software Engineering
School of Computer Science and Technology, Xidian University
2017-2021

News

2026.05
One first-authored paper got accepted by KDD 2026.
2026.04
One co-authored paper got accepted by ACL 2026.
2026.01
One co-authored paper got accepted by EACL 2026.
2025.08
Two co-authored papers got accepted by CIKM 2025.
2025.08
Invited to serve as a PC member for AAAI 2026.
2025.04
One first-authored paper got accepted by SIGIR 2025.
2024.12
Invited to serve as a PC member for WWW 2025.
2024.07
One co-authored paper got accepted by CIKM 2024.
2024.04
One co-authored paper got accepted by IJCAI 2024.
2024.02
Invited to serve as a reviewer for ACL Rolling Review.
2023.12
One first-authored paper got accepted by AAAI 2024.
2023.05
One first-authored paper got accepted by ACL 2023.

Research Highlights

EvoFEND overview
EvoFEND: Dual Memory-Driven Self-Evolving Fake News Detection
Beizhe Hu, Qiang Sheng, Hao Mi, Jiaying Wu, Zhengjia Wang, Yuanlong Yu, Danding Wang, Xuming Hu, Juan Cao
KDD 2026 First Author
TL;DR: We build an agentic framework for fake news detection that can evolve itself by reading social media streams.
Truth Decay project overview
LLM-Generated Fake News Induces Truth Decay in News Ecosystem
Beizhe Hu, Qiang Sheng, Juan Cao, Yang Li, Danding Wang
SIGIR 2025 First Author
TL;DR: We reveal the truth-decay phenomenon where real news gradually loses its top-ranked advantage against fake news as LLM-generated news penetrates.
Preprint Paper Project
ARG framework overview
Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, Peng Qi
AAAI 2024 First Author
TL;DR: Large LMs generally underperform fine-tuned small LMs for fake news detection, but they can be good advisors by providing rationales.
Preprint Paper Code
FTT framework overview
Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection
Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin
ACL 2023 First Author
TL;DR: We address temporal shift in real-world fake news detection by forecasting topic-level trends and adjusting detector updates accordingly.
Preprint Paper Code

Publications

Preprints

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning
Yuhui Shi, Yehan Yang, Qiang Sheng, Hao Mi, Beizhe Hu, Chaoxi Xu, Juan Cao
Preprint [Paper]

2026

EvoFEND: Dual Memory-Driven Self-Evolving Fake News Detection
Beizhe Hu, Qiang Sheng, Hao Mi, Jiaying Wu, Zhengjia Wang, Yuanlong Yu, Danding Wang, Xuming Hu, Juan Cao
KDD 2026
Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework
Xinle Pang, Danding Wang, Qiang Sheng, Yifan Sun, Beizhe Hu, Juan Cao
EACL 2026 [Paper]
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao
ACL 2026 [Preprint]

2025

Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
Zhengjia Wang, Qiang Sheng, Danding Wang, Beizhe Hu, Juan Cao
CIKM 2025 [Preprint] [Paper]
Enhancing Fake News Video Detection via LLM-Driven Creative Process Simulation
Yuyan Bu, Qiang Sheng, Juan Cao, Shaofei Wang, Peng Qi, Yuhui Shi, Beizhe Hu
CIKM 2025 [Preprint] [Paper]
LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation
Beizhe Hu, Qiang Sheng, Juan Cao, Yang Li, Danding Wang
SIGIR 2025 [Preprint] [Paper] [Project]

2024

Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
Qiong Nan, Qiang Sheng, Juan Cao, Beizhe Hu, Danding Wang, Jintao Li
CIKM 2024 [Preprint] [Paper] [Code]
Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
Yuhui Shi, Qiang Sheng, Juan Cao, Hao Mi, Beizhe Hu, Danding Wang
IJCAI 2024 [Preprint] [Code]
Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, Peng Qi
AAAI 2024 [Preprint] [Paper] [Code]

2023

Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection
Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin
ACL 2023 [Preprint] [Paper] [Code]

Honors and Awards

Graduate Honors, University of Chinese Academy of Sciences

  • 2026: Efund PhD Scholarship
  • 2025: First-Class Academic Scholarship; Merit Student
  • 2024: Pacemaker to Merit Student; Academic Scholarship
  • 2023: National Scholarship, Ministry of Education of China; First-Class Academic Scholarship; Merit Student
  • 2022: Academic Scholarship

Undergraduate Honors, Xidian University

  • 2019, 2020: First-Class Academic Scholarship
  • 2018, 2021: Second-Class Academic Scholarship

Academic Services

PC Member
AAAI 2026, TheWebConf (WWW) 2025
Reviewer
KDD 2026, ACL Rolling Review (Feb. 2024-present)