I am a senior undergraduate at Peking University working with Prof. Xiaojun Wan. I was an undergraduate visiting researcher (UGVR) at Stanford University, advised by Prof. Diyi Yang.

My research explores how AI systems adapt to (1) tasks, (2) users, and (3) social contexts.

  • Task Adaptivity: Improving how LLMs retrieve, select, and structure contextual knowledge for diverse tasks.
  • User Adaptivity: Developing interaction mechanisms that allow agents to adapt to evolving user goals and preferences.
  • Social Adaptivity: Studying how social factors influence model decisions to build socially aware and fair AI systems.

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]

Awards

  • 2025: Peking University Person of the Year Nomination (45/65k+, blog spotlight in Chinese)
  • 2025: National Scholarship (1%, Rank1)
  • 2025: Peking University Merit Student (Rank1)
  • 2024: Leo KoGuan Scholarship (1%)
  • 2023-2024: Peking University Merit Student Pacesetter (1%, Rank 1)
  • 2024: CSDN Blog Star of the Year (Top 87)
  • 2023: Peking University Person of the Year Nomination (Youngest Nominee, 45/65k+, blog spotlight in Chinese)
  • 2023: Peking University May 4th Scholarship (1%, Rank 1)
  • 2023: CSDN Blog Star (Beijing Top10)
  • 2023: Kaggle House Price Prediction Competition (1%)
  • 2023: Tianchi BMW Hackathon (Rank 1)
  • 2023: Peking University Hackathon WebGPU Track (Rank 2)
  • 2023: Greater Bay Area International Algorithm Competition, Finalist