I am a senior undergraduate student in the Department of Information Management, Peking University. I am fortunate to work as a research assistant at Wangxuan Institute of Computer Technology under the guidance of Prof. Xiaojun Wan. In Summer 2025, I joined the Stanford SALT Lab as an undergraduate visiting researcher (UGVR), advised by Prof. Diyi Yang.

I believe adaptivity is essential for AI systems operating in real-world settings. My research explores how such systems can adapt (1) to the tasks they solve, (2) the users they interact with, and (3) the social contexts they operate in.

• Task Adaptivity: Enhancing how LLMs retrieve, select, and structure contextual knowledge to solve diverse tasks reliably.
• User Adaptivity: Developing interaction mechanisms that allow agents to adapt to users’ evolving goals and preferences over long time horizons.
• Social Adaptivity: Investigating how social factors shape model decisions to build systems that are socially aware, fair, and unbiased across different demographics.

Selected Publications

• Who Writes What: Unveiling the Impact of Author Roles on AI-generated Text Detection
  Jiatao Li, Xiaojun Wan
  ACL 2025. (Long Paper) [pdf]

• Where Do LLMs Go Wrong? Diagnosing Automated Peer Review via Aspect-Guided Multi-Level Perturbation
  Jiatao Li, Yanheng Li, Xinyu Hu, Mingqi Gao, Xiaojun Wan
  CIKM 2025. (Long Paper) [pdf]

• Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
  Jiatao Li, Xinyu Hu, Xunjian Yin, Xiaojun Wan
  NAACL 2025 (Findings). (Long Paper) [pdf]

Preprints

• SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
  Jiatao Li, Xinyu Hu, Xiaojun Wan
  arXiv:2409.13992 [pdf]

• Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview
  Jiatao Li, Yanheng Li, Xiaojun Wan
  arXiv:2505.01967 [pdf]

• AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection
  Jiatao Li, Mao Ye, Cheng Peng, Xunjian Yin, Xiaojun Wan
  arXiv:2505.15261 [pdf]

Selected Awards

• 2025: Peking University Annual Person of the Year Nomination (45/65k+, blog spotlight in Chinese)
• 2025: National Scholarship (China’s highest-level undergraduate scholarship)
• 2025: Peking University Merit Student
• 2024: Leo KoGuan Scholarship
• 2023-2024: Peking University Merit Student Pacesetter
• 2024: CSDN Blog Star of the Year Top87
• 2023: Peking University Annual Person of the Year Nomination (Youngest Nominee, 45/65k+, blog spotlight in Chinese)
• 2023: Peking University May 4th Scholarship (Highest-level Scholarship in Peking University, 125/65k+)
• 2023: CSDN Blog Star (Beijing) Top10
• 2023: Kaggle Competition:HousePrice Prediction Top1%
• 2023: Tianchi BMW 3rd Hackathon - Virtual Collaborative Co-Creation Track & Finals Rank1
• 2023: Peking University Hackathon Track2(WebGPU) Rank2
• 2023: Greater Bay Area (Huangpu) International Algorithm Case Competition - Advanced Enhancement of Large Language Model Comprehensive Abilities (Pazhou Laboratory & Fudan University), Finalist.