Shichao Song
宋世超

I am Shichao Song, a second-year PhD student. My current research focuses on large language models, specifically on two aspects: internal consistency mining (which can be understood as hallucination mitigation and reasoning enhancement, as discussed in ICSFSurvey) and reliable evaluation for LLMs (such as UHGEval, xFinder, TurtleBench, and SituEval). Previously, my research has covered topics like route optimization, recommender systems, and graph neural networks.

More: E-mail / X / LinkedIn / Google Scholar / Prophy / GitHub / Hugging Face / CV / 💘

---

H2 Education

• Renmin University of China
  Ph.D. in Computer Application Technology
  Supervised by Prof. Xun Liang
  2023.09 - Present

• 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%
  2019.09 - 2023.06

H2 Work Experience

• Institute for Advanced Algorithms Research, Shanghai
  Research Intern at the Large Language Model Center
  Supervised by Dr. Zhiyu Li
  2023.09 - Present

H2 Researches

^* Contributed Equally
^† Corresponding Author

H3 Peer Reviewed

• xFinder: Robust and Pinpoint Answer Extraction for Large Language Models
  Qingchen Yu^*, Zifan Zheng^*, Shichao Song^*, Zhiyu Li^†, Feiyu Xiong, Bo Tang, Ding Chen
  ICLR, 2025.04. ICLR / arXiv / GitHub / Hugging Face / WeChat Article

• Attention Heads of Large Language Models: A Survey
  Zifan Zheng^*, Yezhaohui Wang^*, Yuxin Huang^*, Shichao Song, Mingchuan Yang, Bo Tang, Feiyu Xiong, Zhiyu Li^†
  Patterns, 2025.02. Cell Press / arXiv / GitHub / Hugging Face

• Memory³: Language Modeling with Explicit Memory
  Hongkang Yang^†, Zehao Lin, Wenjin Wang, Hao Wu, Zhiyu Li, Bo Tang, Wenqiang Wei, Jinbo Wang, Zeyun Tang, Shichao Song, Chenyang Xi, Yu Yu, Kai Chen, Feiyu Xiong, Linpeng Tang, Weinan E
  J. Mach. Learn., 2024.09. Global Science Press / arXiv / X Thread / WeChat Article

• UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
  Xun Liang^*, Shichao Song^*, Simin Niu^*, Zhiyu Li^†, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Peng Cheng, Zhonghao Wang, Haiying Deng
  ACL, 2024.08. ACL Anthology / arXiv / GitHub / Eval Suite / UHGEvalDataset / Dataset Creation / WeChat Article

• Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
  Xun Liang^*, Hanyu Wang^*, Shichao Song^*, Mengting Hu, Xunzhi Wang, Zhiyu Li^†, Feiyu Xiong, Bo Tang
  Findings of ACL, 2024.08. ACL Anthology / arXiv / GitHub / WeChat Article

• When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract)
  Simin Niu, Xun Liang^†, Sensen Zhang, Shichao Song, Xuan Zhang, Xiaoping Zhou
  AAAI, 2024.03. AAAI Press

H3 Preprints

• SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
  Xun Liang, Simin Niu, Zhiyu Li^†, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Jason Zhaoxin Fan, Bo Tang, Shichao Song, Mengwei Wang, Jiawei Yang
  arXiv, 2025.01. arXiv / GitHub

• TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles
  Qingchen Yu^*, Shichao Song^*, Ke Fang^*, Yunfeng Shi, Zifan Zheng, Hanyu Wang, Simin Niu, Zhiyu Li^†
  arXiv, 2024.10. arXiv / GitHub / TurtleBench1.5k / Online Game / Blog Post

• Controllable Text Generation for Large Language Models: A Survey
  Xun Liang^*, Hanyu Wang^*, Yezhaohui Wang^*, Shichao Song, Jiawei Yang, Simin Niu, Jie Hu, Dan Liu, Shunyu Yao, Feiyu Xiong, Zhiyu Li^†
  arXiv, 2024.08. arXiv / GitHub / Hugging Face / PDF in Chinese / X Thread / WeChat Article

• Internal Consistency and Self-Feedback in Large Language Models: A Survey
  Xun Liang^*, Shichao Song^*, Zifan Zheng^*, Hanyu Wang, Qingchen Yu, Xunkai Li, Rong-Hua Li, Yi Wang, Zhonghao Wang, Feiyu Xiong, Zhiyu Li^†
  arXiv, 2024.07. arXiv / GitHub / Hugging Face / X Thread / WeChat Article

• HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability
  Yanfang Chen^*, Ding Chen^*, Shichao Song, Simin Niu, Hanyu Wang, Zeyun Tang, Feiyu Xiong, Zhiyu Li^†
  arXiv, 2024.07. arXiv / GitHub

• Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning
  Xun Liang^*, Simin Niu^*, Zhiyu li^†, Sensen Zhang, Shichao Song, Hanyu Wang, Jiawei Yang, Feiyu Xiong, Bo Tang, Chenyang Xi
  arXiv, 2024.05. arXiv / GitHub / WeChat Article

• Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities
  Xiaomin Yu^*, Yezhaohui Wang^*, Yanfang Chen^†, Zhen Tao, Dinghao Xi, Shichao Song, Simin Niu, Zhiyu Li
  arXiv, 2024.05. arXiv

• Grimoire is All You Need for Enhancing Large Language Models
  Ding Chen^*, Shichao Song^*, Qingchen Yu, Zhiyu Li^†, Wenjin Wang, Feiyu Xiong, Bo Tang
  arXiv, 2024.01. arXiv / GitHub / WeChat Article

H3 Unpublished

• Research on Cold-Start of Product Recommendation with Graph Neural Network (In Chinese, 基于图神经网络的商品推荐冷启动研究)
  Shichao Song
  Undergraduate thesis, 2023.05. Outstanding Undergraduate Thesis. PDF / GitHub

• Advances in Graph Meta-Learning (In Chinese, 图元学习研究进展)
  Simin Niu, Xun Liang^†, Chen Feng, Sensen Zhang, Shichao Song, Hanyu Wang
  Unpublished, 2023.05.

• Optimization of Emergency Supplies Distribution Across Risk Areas During the Pandemic (In Chinese, 疫情下的应急物资跨风险区域配送优化)
  Yongzhe Gao, Shichao Song, Qingchen Yu, Xiaodong Shi^†
  Unpublished, 2022.02. GitHub

H2 Selected Awards and Honors

• First-Class Academic Scholarship for Doctoral Students
  Renmin University of China, 2024.11

• Second-Class Academic Scholarship for Doctoral Students
  Renmin University of China, 2023.11

• National Encouragement Scholarship (Rank: Top 5%)
  Henan University of Economics and Law, 2022.11

• National Second Prize in the China Undergraduate Mathematical Contest in Modeling
  China Society for Industrial and Applied Mathematics, 2021.11

• National Encouragement Scholarship (Rank: Top 5%)
  Henan University of Economics and Law, 2020.11

H2 Services

• Reviewer for ICLR’25, ACM TIST
• Volunteer at AI TIME

---