Scholar
Shicheng Liu
Google Scholar ID: Qu38o2EAAAAJ
CS PhD Candidate, Stanford University
Citations & Impact
Citations
211
H-index
7
i10-index
7
Publications
14
Co-authors
0
Publications
Resume
Academic Achievements
- 1. SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning (pre-print, under review)
- 2. SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models (Findings of NAACL 2024)
- 3. SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions (Findings of EMNLP 2024)
- 4. Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata (EMNLP 2023)
- 5. Coding Reliable LLM-based Integrated Task and Knowledge Agents with GenieWorksheets (Proceedings of ACL 2025)
Research Experience
- 1. AI research intern at Meta during summer 2025, working with Kai Sun, Scott Yih, and Luna Dong on RL for knowledge extraction.
Education
- 1. Ph.D in Computer Science, Stanford University, 2022 - 2026 (Expected), Advisor: Prof. Monica S. Lam
- 2. B.S. (w. Honors) in Computer Science & in Mathematics, Minor in Physics, The University of Chicago, 2022
- 3. Quarter-long exchange, California Institute of Technology, Autumn 2021
Background
- Fourth-year CS Ph.D. at Stanford focusing on real-life, practical NLP problems, often drawing perspectives from computer systems and programming languages. Recent research focuses on knowledge agents with LLMs, aiming to enable domain-independent approaches that effectively retrieve and navigate different sources of knowledge, including structured, unstructured, and hybrid data.