Hi there! I am Shicheng Liu, fourth-year CS Ph.D. at Stanford advised by Prof. Monica S. Lam at Stanford Open Virtual Assistant Lab (OVAL) and Stanford NLP Group. My research focuses on knowledge agents with LLMs, aiming to enable domain-independent approaches for in-depth exploration and synthesis of information from diverse knowledge sources, including structured, unstructured, and hybrid sources. Some of my recent work includes reinforcement learning approaches (SCRIBES, ICLR 2026; work done at Meta), agentic frameworks (SPINACH, EMNLP 2024), and programming-language interfaces for LLMs (SUQL, NAACL 2024) to tackle this problem.

I am grateful to be supported by the 2025-2026 IBM PhD Fellowship Award.

Education

• Ph.D in Computer Science
  Stanford University, 2022 - 2026 (Expected)

• B.S. (w. Honors) in Computer Science & in Mathematics, Minor in Physics
  The University of Chicago, 2022

  • Quarter-long exchange (Autumn 2021), California Institute of Technology

Selected Recent Publications

^† Denotes joint first authorship.

• LLMs with Structured and Unstructured data

  • SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
    Shicheng Liu, Kai Sun, Lisheng Fu, Xilun Chen, Xinyuan Zhang, Zhaojiang Lin, Rulin Shao, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
    Accepted to The Fourteenth International Conference on Learning Representations (ICLR 2026)
    

  • SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models
    (10-min video presentation)
    Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Sina J. Semnani, Chen Jie Yu, Monica S. Lam
    Findings of the North American Chapter of Association for Computational Linguistics (NAACL 2024)
    

• LLMs with Knowledge Graph

  • SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions
    (10-min video presentation)
    Shicheng Liu^†, Sina J. Semnani^†, Harold Triedman, Jialiang Xu, Isaac Dan Zhao, Monica S. Lam
    Findings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
    

  • Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata
    (6-min video presentation)
    Silei Xu^†, Shicheng Liu^†, Theo Culhane, Elizaveta Pertseva, Meng-Hsi Wu, Sina Semnani, Monica S. Lam
    The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
    

• Programmable Task and Knowledge Agents with LLMs
  • Coding Reliable LLM-based Integrated Task and Knowledge Agents with GenieWorksheets
    Harshit Joshi, Shicheng Liu, James Chen, Robert Weigle, Monica S. Lam
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)