Shicheng Liu

About

Hi there! I am a final-year CS Ph.D. candidate at Stanford, advised by Prof. Monica S. Lam at the 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 — structured, unstructured, and hybrid. Some of my recent work includes reinforcement learning approaches (SCRIBES, ICLR 2026; work done at Meta), agentic frameworks (DataSTORM, COLM 2026; SPINACH, EMNLP 2024), and programming-language interfaces for LLMs (SUQL, NAACL 2024) to tackle this problem. Previously, I interned at Databricks and Meta.

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. (with Honors) in Computer Science & in Mathematics, minor in Physics, The University of Chicago
2022
- Quarter-long exchange (Autumn 2021), California Institute of Technology

News

Sep 2026Honored to be named a 2026 Rising Star in Data Science by the University of Chicago Data Science Institute. Looking forward to presenting at the workshop in November.
Sep 2026Wrapped up my summer research internship at Databricks, where I bridged a research collaboration with Stanford. Check out our paper on AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery.
Jul 2026DataSTORM, our deep-research system for large-scale databases, is accepted to COLM 2026.
Jun 2026Thrilled to represent Stanford at Databricks' inaugural Grounded Reasoning Cup — and we won 1st place! Thank you to our mentors from Anthropic. Check out our winning solution in Databricks' writeup.
Jan 2026SCRIBES (work done at Meta) is accepted to ICLR 2026.
Jan 2026Honored to receive the IBM PhD Fellowship Award (2025–2026).

Selected Publications

^† denotes joint first authorship. Full list on Google Scholar.

AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery

Shicheng Liu, Krista Opsahl-Ong, Andrew Drozdov, Julian Killingback, Arnav Singhvi, Ronak Pradeep, Michael Bendersky, James C. Dickerson, Monica S. Lam

PreprintWork done at Databricks

DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling

Shicheng Liu, Yucheng Jiang, Sajid Farook, Camila Nicollier Sanchez, David Fernando Castro Pena, Monica S. Lam

COLM 2026Code

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

ICLR 2026Work done at MetaCode

Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets

Harshit Joshi, Shicheng Liu, James Chen, Robert Weigle, Monica S. Lam

ACL 2025Code

SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

Shicheng Liu^†, Sina J. Semnani^†, Harold Triedman, Jialiang Xu, Isaac Dan Zhao, Monica S. Lam

Findings of EMNLP 2024Code Wikimedia Research Newsletter Video

SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models

Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Sina J. Semnani, Chen Jie Yu, Monica S. Lam

Findings of NAACL 2024Code PyPI Video

Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

Silei Xu^†, Shicheng Liu^†, Theo Culhane, Elizaveta Pertseva, Meng-Hsi Wu, Sina Semnani, Monica S. Lam

EMNLP 2023Code Wikimedia Research Newsletter Video

Awards

IBM PhD Fellowship Recipient · 2025–2026
Rising Star in Data Science, The University of Chicago Data Science Institute · 2026
1st Place, Databricks Grounded Reasoning Cup · 2026
Brown Institute Magic Grant · 2024–2025
Top-5% of Stanford CS Course Assistants (Stanford CS224V) · 2023
Graduated Summa Cum Laude, The University of Chicago · 2022
Outstanding Undergraduate Researcher Award, Honorable Mention, CRA · 2022

Beyond Research

Away from the keyboard, I love playing tennis 🎾, badminton 🏸, bouldering 🧗, and most passionately, snowboarding 🏂. If a paper deadline lands on a powder day, my thoughts are with the mountain 🏔️❄ Right after deadlinesYou might see me scrambling for first chairs at Palisades, Heavenly, or sending The Wall off Kirkwood's Chair 10..