Hi! My name is Jing Xiong (熊璟), and I am currently a third-year graduate student at the School of Intelligent Systems Engineering, Sun Yat-sen University, under the supervision of Prof. Xiaodan Liang and Prof. Chengming Li. Before that, I obtained my Bachelor’s degree in Computer Science from Central South University in 2021.

My research interests primarily include natural language processing, complex reasoning based on language models, and formal theorem proving. I am also interested in analyzing and understanding the reasoning capabilities of neural networks using classic machine learning techniques, such as information bottleneck, influence function, and low-rank decomposition method, etc.

During my internship at the Noah’s Ark Lab, I had the opportunity to learn from Dr. Zhengying Liu and Dr. Jianhao Shen. I acquired knowledge in interactive theorem prover Lean and Metamath with a foundation in ZFC set theory. Under the guidance of Dr. Zhengying Liu, I contributed to the development of a prototype theorem verification environment based on based on Metamath for language models. Additionally, I gained insights into structural prediction from Dr. Zhijiang Guo. As a core member under the leadership of Dr. Yichun Yin and Dr. Guo Zhijiang, I actively participated in the development of the PanGu Manifacture Large Model for the OptVerse AI Solver project. This project successfully made its debut at the Huawei HDC 2023 keynote session, and i was honored with the title of “The Star of Manifacture Large Model” in the 2012 Lab.

News

01/2024: A paper is accepted in ICLR 2024.
01/2024: A paper is accepted in ICLR 2024.
11/2023: The paper TRIGO has been selected for an oral presentation at EMNLP 2023.
10/2023: A paper is accepted in EMNLP 2023.
9/2023: A paper has been submitted to ICLR 2024.
9/2023: A paper has been submitted to ICLR 2024.
5/2023: A paper is accepted in ACL 2023.
5/2022: A paper is accepted in SIGIR 2022.

Publications

LEGO-Prover: Neural Theorem Proving with Growing Libraries

Huajian Xin, Haiming Wang, Chuanyang Zheng, Lin Li, Zhengying Liu, Qingxing Cao, Yinya Huang, Jing Xiong, Han Shi, Enze Xie, Jian Yin, Zhenguo Li, Xiaodan Liang, Heng Liao

ICLR, 2024
arXiv, Code

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning

Jing Xiong, Zixuan Li, Chuanyang Zheng, Zhijiang Guo, Yichun Yin, Enze Xie, Zhicheng Yang, Qingxing Cao, Haiming Wang, Xiongwei Han, Jing Tang, Chengming Li, Xiaodan Liang

ICLR, 2024
arXiv, Code

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

EMNLP, 2023
arXiv, Code

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

ACL, 2023
arXiv

Expression Syntax Information Bottleneck for Math Word Problems

Jing Xiong, Chengming Li, Min Yang, Xiping Hu, Bin Hu

SIGIR, 2022
arXiv, Code

Self-consistent Reasoning For Solving Math Word Problems

Jing Xiong, Zhongwei Wan, Xiping Hu, Min Yang, Chengming Li

arXiv, Code

CV

Please check my resume here.