Shengnan An

Shengnan An

I am a final-year Ph.D. candidate working in Xi’an Jiaotong University and Microsoft Research Asia. My research interest is to explore reasoning capabilities in large language models, such as mathematical reasoning, inductive reasoning, and long-context reasoning.

📝 Publications

  • Make Your LLM Fully Utilize the Context. (NeurIPS 2024) [Paper] [Code]
    Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen.
  • Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation. (under review)
    Zexiong Ma, Shengnan An, Zeqi Lin, Nanning Zheng, Jian-Guang Lou.
  • Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks. (EMNLP 2024) [Paper] [Code]
    Shengnan An, Zexiong Ma, Siqi Cai, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen.
  • Learning From Mistakes Makes LLM Better Reasoner. (arXiv version of our EMNLP 2024 paper) [Paper]
    Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen.
  • STAND-Guard: A Small Task-Adaptive Content Moderation Model. (COLING 2025) [Paper]
    Minjia Wang, Pingping Lin, Siqi Cai, Shengnan An, Shengjie Ma, Zeqi Lin, Congrui Huang, Bixiong Xu
  • Compositional API Recommendation for Library-Oriented Code Generation. (ICPC 2024) [Paper]
    Zexiong Ma, Shengnan An, Bing Xie, Zeqi Lin.
  • Skill-Based Few-Shot Selection for In-Context Learning. (EMNLP 2023) [Paper]
    Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, B. Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou.
  • How Do In-Context Examples Affect Compositional Generalization? (ACL 2023) [Paper] [Code]
    Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, Dongmei Zhang.
  • Does Deep Learning Learn to Abstract? A Systematic Probing Framework. (ICLR 2023) [Paper] [Code]
    Shengnan An, Zeqi Lin, Bei Chen, Qiang Fu, Nanning Zheng, Jian-Guang Lou.
  • Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models. (arXiv) [Paper]
    Shengnan An*, Yifei Li*, Zeqi Lin, Qian Liu, Bei Chen, Qiang Fu, Weizhu Chen, Nanning Zheng, Jian-Guang Lou.
  • Learning Algebraic Recombination for Compositional Generalization. (ACL 2021) [Paper] [Code]
    Chenyao Liu*, Shengnan An*, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng, Dongmei Zhang.
  • Compositional Generalization by Learning Analytical Expressions. (NeurIPS 2020 Spotlight) [Paper] [Code]
    Qian Liu*, Shengnan An*, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, Dongmei Zhang.

📖 Educations

  • 2020.09 - 2025.06, Xi’an Jiaotong University, Ph.D Candidate. Adviser: Prof. Nanning Zheng.
  • 2019.09 - 2025.06, Microsoft Research Asia, Joint Ph.D Program. Adviser: Jian-Guang Lou. Mentor: Zeqi Lin.
  • 2016.09 - 2020.06, Xi’an Jiaotong University, Bachelor’s Degree. Honorable Degree for Qian Xuesen Class (钱学森班).

☀️ Honors and Awards

  • National Scholarship (2024)
  • China Mobile Scholarship (2024)
  • Outstanding Graduate Student (2023)
  • Outstanding Graduate Cadre (2020)
  • Star of Tomorrow in MSRA (2019, 2020)
  • Outstanding Student Cadre (2017, 2018, 2019)
  • First Class Scholarship (2017, 2019)

🌿 Academic Service

Reviewer for: NeurIPS, ICLR, ICML, ACL Rolling Review（ACL, EMNLP, NAACL, EACL）