I am Fangzhi Xu (徐方植), a first-year PhD student in Xi’an Jiaotong University, major in Computer Science, advised by Prof. Jun Liu. Also, I am currently a research intern at Shanghai AI LAB, supervised by Dr. Zhiyong Wu. In 2021, I received the B.S. degree in Electrical Engineering from Xi’an Jiaotong University.

I have published researches in some top-tier conferences and journals, such as ACL, SIGIR, IEEE TKDE, and IEEE TNNLS. Also, I serve as a PC member (or reviewer) for IJCAI, SIGIR and IEEE TNNLS.

My research interests include (but not limited to) natural language processing, large language models and neuro-symbolic reasoning.

🔥 News

2024.03.24: Our recent survey on neural code intelligence is made public 🎉🎉!
2024.03.11: One paper is accepted by LLMAgent Workshop @ICLR 2024 🎉🎉!
2024.02.20: One paper is accepted by COLING 2024 🎉🎉!
2024.02.15: One paper [SeeClick] is submitted to ACL-ARR (Feb. 2024) !
2024.02.10: One paper is accepted by ICDE 2024 (TKDE Poster Track) 🎉🎉!
2023.12.15: Two papers [Symbol-LLM, PathReasoner] are submitted to ACL-ARR (Dec. 2023) !
2023.11.15: We make the recent work Symbol-LLM public 🚀!
2023.09.12: One paper is accepted by IEEE TNNLS 🎉🎉!
2023.05.02: One paper is accepted by ACL 2023 🎉🎉!

📖 Educations

2023.09 - 2026.06 (expected), PhD student in Computer Science, Xi’an Jiaotong University.
2021.09 - 2023.06, M.S. in Computer Science, Xi’an Jiaotong University. GPA:91.77/100, Rankings:1/173
2017.09 - 2021.06, B.S. in Electrical Engineering, Xi’an Jiaotong University. GPA:97.62/100, Rankings:1/365

💻 Internships

2023.07 - Present, Research Intern @ Shanghai AI LAB. Focus on Large Language Models and Neuro-Symbolic.

📝 Publications

Preprint

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond 🔥🔥 [Preprint]
Qiushi Sun, Zhirui Chen, Fangzhi Xu, Chang Ma, Kanzhi Cheng, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Pengcheng Yin, Qipeng Guo, Xipeng Qiu, Xiaoli Li, Fei Yuan, Lingpeng Kong, Xiang Li, Zhiyong Wu

Code

We make a thorough conclusion of the paradigm shifts on neural code intelligence and provide extensive insights on advances and future directions. Check it out!

Preprint

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models 🔥🔥 [Preprint]
Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Qiao Yu and Jun Liu.

Code Project Page

Preprint

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond [Preprint]
Fangzhi Xu*, Qika Lin*, Jiawei Han, Tianzhe Zhao, Jun Liu and Erik Cambria

(* means equal contributions)

Code

This paper provides a systematic, comprehensive and fine-level evaluation of logical reasoning capability from deductive, inductive and abductive views.
We propose a new dataset named NeuLR. It contains 3K samples with neutral content, covering deductive, inductive and abductive reasoning manners.

Under Review

PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering [Under Review]
Fangzhi Xu, Qika Lin, Tianzhe Zhao, Jiawei Han, Jun Liu

Code

We are the first to rethink the logical reasoning task by unifying the inputs into atoms and reasoning paths.
We propose an atom extension strategy with equivalent logical formulas to generate diverse new samples. Also, we introduce a stack of transformer-style blocks. Specifically, a path-attention module with high-order relation modeling is proposed to joint update information within and across atoms.

SIGIR 2022

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning [CCF-A]
Fangzhi Xu, Jun Liu, Qika Lin, Yudai Pan and Lingling Zhang

Code

Logiformer is a two-branch network for the logical reasoning task in the field of multiple-choice machine reading comprehension.
Up to publication, it is the state-of-the-art (SOTA) model compared with all the RoBERTa-Large based single model methods. Also, it ranks on the 9th place in the leaderboard compared with other larger models.

IEEE TNNLS

Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text [CCF-B]
Fangzhi Xu, Jun Liu, Qika Lin, Tianzhe Zhao, Jian Zhang, Lingling Zhang

Code

We propose the first benchmark for generalized zero-shot logical reasoning, named ZsLR
A strong baseline TaCo is proposed, which is based on contrastive learning.

Pattern Recognition

MoCA: Incorporating Domain Pretraining and Cross Attention for Textbook Question Answering [CCF-B]
Fangzhi Xu, Qika Lin, Jun Liu, Lingling Zhang, Tianzhe Zhao, Qi Chai, Yudai Pan

Code

MoCA focuses on the task of Textbook Question Answering, which is a multimodal task with abundant diagrams and large context.
It conducts multi-stage pretraining on the text part and introduces dense layers of cross-guided multimodel attention for the diagram part.

🧑‍ Other Paper

ICLR 2024 Workshop SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents [Arxiv]
Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, Zhiyong Wu
COLING 2024 A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction [CCF-B]
Jian Zhang, Changlin Yang, Haiping Zhu, Qika Lin, Fangzhi Xu and Jun Liu
ACL 2023 TECHS: Temporal Logical Graph Networks for Explainable Extrapolation Reasoning [CCF-A]
Qika Lin, Jun Liu, Rui Mao, Fangzhi Xu and Erik Cambria
Information Fusion Fusing Topology Contexts and Logical Rules in Language Models for Knowledge Graph Completion [SCI-Q1]
Qika Lin, Rui Mao, Jun Liu, Fangzhi Xu, Erik Cambria
APWEB-WAIM 2022 Incorporating Prior Type Information for Few-shot Knowledge Graph Completion [CCF-C] (Excellent Student Paper)
Siyu Yao, Tianzhe Zhao, Fangzhi Xu, Jun Liu
SIGIR 2022 Incorporating Context Graph with Logical Reasoning for Inductive Relation Prediction [CCF-A]
Qika Lin, Jun Liu, Fangzhi Xu, Yudai Pan, Yifan Zhu, Lingling Zhang and Tianzhe Zhao
IEEE TKDE Contrastive Graph Representations for Logical Formulas Embedding [CCF-A]
Qika Lin, Jun Liu, Lingling Zhang, Yudai Pan, Xin Hu, Fangzhi Xu, Hongwei Zeng

🎖 Honors and Awards

Honors

Oct.2022 Outstanding Student in Xi’an Jiaotong University
Jun.2021 Outstanding Undergraduate Graduates in Shaanxi Province
Sep.2020 Top-10 Students of the Year (Top Personal Award in Xi’an Jiaotong University)
Sep.2019 Outstanding Student in Xi’an Jiaotong University
Sep.2018 Outstanding Student in Xi’an Jiaotong University

Competition Awards

Dec.2022 ”Huawei Cup” Mathematical Contest in Modeling, Second Prize
Mar.2022 Asia and Pacific Mathematical Contest in Modeling (APMCM), First Prize + Innovation Award (Top-2)
Dec.2021 ”Huawei Cup” Mathematical Contest in Modeling, Second Prize
Sep.2020 IKCEST International Big Data Competition, Excellence Award
Apr.2020 Mathematical Contest in Modeling (COMAP), Finalist
Dec.2019 China Mathematical Contest in Modeling (CUMCM), Second Prize
May.2018 National English Competition for College Students (NECCS), Second Prize

🎖 Scholarships

2023.09 Freshman First Prize Scholarship (PhD)
2022.09 National Scholarship
2022.09 Huawei Scholarship
2022.04 ACM SIGIR Student Travel Grant
2021.09 Freshman First Prize Scholarship (Master)
2020.09 Chinese Modern Scientists Scholarship (Only for Top-10 Student)
2019.09 National Scholarship
2018.09 National Scholarship

💬 Academic Services

Program Committee Member: IJCAI 2024, SIGIR 2024, AACL 2023, SIGIR 2023, SIGIR-AP 2023
Reviewer: IEEE TNNLS