H2 Education
Renmin University of China
Ph.D. in Computer Application Technology
Supervised by Prof. Xun Liang
Sep 2023 - Jun 2028
Henan University of Economics and Law
B.Mgt. in E-commerce
Supervised by Prof. Yong Pan and Prof. Xiaodong Shi
GPA: 4.05/5.0, Top 2%
Sep 2019 - Jun 2023
H2 Work Experience
Ant Group
Research Intern at Ant Research
Collaborated with Director, Qing Shao
Jul 2025 - Present
Institute for Advanced Algorithms Research, Shanghai
Research Intern at the Large Language Model Center
Collaborated with Dr. Zhiyu Li and Dr. Zehao Lin
Sep 2023 - Jun 2025
H2 Selected Researches
Refer to my Google Scholar for complete list of publications.
H3 Structured Generation
Guided Infilling Modeling: Mining Knowledge from LLMs as Probabilistic Databases
Shichao Song*, Qingchen Yu, Huayi Lai, Mengwei Wang, et al.
Under Review.
H3 LLM Evaluation
TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles
Qingchen Yu*, Shichao Song*, Ke Fang*, Yunfeng Shi, et al.
ICASSP, May 2026.
IEEE / arXiv / GitHub / TurtleBench1.5k / Online Game / Blog Post
xFinder: Robust and Pinpoint Answer Extraction for Large Language Models
Qingchen Yu*, Zifan Zheng*, Shichao Song*, Zhiyu Li†, et al.
ICLR, Apr 2025.
ICLR / arXiv / GitHub / Hugging Face / WeChat Article
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
Xun Liang*, Shichao Song*, Simin Niu*, Zhiyu Li†, et al.
ACL, Aug 2024.
ACL Anthology / arXiv / GitHub / Eval Suite / UHGEvalDataset / Dataset Creation / WeChat Article
H3 Others
MemOS: A Memory OS for AI System
Zhiyu Li, Shichao Song, Chenyang Xi, Hanyu Wang, et al.
arXiv, Jul 2025.
Website / arXiv / GitHub / X Thread / WeChat Article
Internal Consistency and Self-Feedback in Large Language Models: A Survey
Xun Liang*, Shichao Song*, Zifan Zheng*, Hanyu Wang, et al.
arXiv, Jul 2024.
arXiv / GitHub / Hugging Face / X Thread / WeChat Article
Grimoire is All You Need for Enhancing Large Language Models
Ding Chen*, Shichao Song*, Qingchen Yu, Zhiyu Li†, et al.
arXiv, Jan 2024.