Shicheng Liu

Final-year Ph.D. Candidate, Stanford Computer Science
Stanford NLP Group · Stanford OVAL

Email Google Scholar GitHub CV X
Portrait of 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.

Over the summer of 2026, I am spending time at Databricks, bridging a research collaboration with Stanford. Previously, I interned at Meta Reality Labs and Meta FAIR.

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

Education

News

Selected Publications

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

LLM-based Deep Research Systems for Databases

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 2026

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

ICLR 2026Work done at Meta
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 2024CodePyPIVideo

LLMs with Knowledge Bases

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 2024CodeWikimedia Research NewsletterVideo
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 2023CodeWikimedia Research NewsletterVideo

Programmable Task and Knowledge Agents with LLMs

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

Awards

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..