Zhenwen Liang (梁振文)  

Research Scientist

Tencent America,
Bellevue, Washington


Email: zhenwzliang@global.tencent.com


About me


From Jan 2025, I start working as a Research Scientist at Tencent America. Feel free to reach out if you want to apply for internship.
I obtained my PhD degree at the University of Notre Dame. My supervisor is Professor Xiangliang Zhang.

Prior to Notre Dame, I got my B.E. degree in Computer Science at University of Electronic Science and Technology of China (UESTC) and my M.S degree in King Abdullah University of Science and Technology (KAUST).

My research interests include Natural Language Processing, Mathematical Question Answering, Large Language Models, Multimodal Reasoning, etc.

News

Education

Organization of Tutorials and Workshops

Selected Publications

  • Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
    Zhenwen Liang, Ye Liu, Tong Niu, Xiangliang Zhang, Yingbo Zhou, Semih Yavuz
    Arxiv Preprint. [Paper]

  • MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
    Zhenwen Liang, Dian Yu, Wenhao Yu, Wenlin Yao, Zhihan Zhang, Xiangliang Zhang, Dong Yu
    Arxiv Preprint. [Paper]

  • SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark
    Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang
    ACL 2024. [Paper, Code]

  • MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
    Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu
    LREC-COLING 2024. [Paper]

  • Defending Jailbreak Prompts via In-Context Adversarial Game
    Yujun Zhou, Yufei Han, Haomin Zhuang, Taicheng Guo, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
    EMNLP 2024. [Paper]

  • Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples
    Qingkai Zeng, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Zhenwen Liang, Zhihan Zhang, Meng Jiang
    CIKM 2024. [Paper]

  • Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation
    Zhenwen Liang, Wenhao Yu, Tanmay Rajpurohit, Peter Clark, Xiangliang Zhang, Ashwin Kaylan
    EMNLP 2023. [Paper, Code]

  • UniMath: A Foundational and Multimodal Mathematical Reasoner
    Zhenwen Liang, Tianyu Yang, Jipeng Zhang, Xiangliang Zhang
    EMNLP 2023. [Paper, Code]

  • Improving language models via plug-and-play retrieval feedback
    Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, Ashish Sabharwal
    Arxiv Preprint. [Paper]

  • Don't be Blind to Questions: Question-Oriented Math Word Problem Solving
    Zhenwen Liang, Jipeng Zhang and Xiangliang Zhang.
    IJCNLP-AACL 2023

  • What indeed can GPT models do in chemistry? A comprehensive benchmark on eight tasks
    Taicheng Guo, Kehan Guo, Bozhao nan, Zhenwen Liang, Zhichun Guo, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang
    NeurIPS 2023 Dataset&Benchmark Track. [Paper]

  • Compositional Mathematical Encoding for Math Word Problems
    Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, Xiangliang Zhang
    ACL 2023 - Findings

  • Generalizing Math Word Problem Solvers via Solution Diversification
    Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang
    AAAI 2023 [Paper]

  • Analogical Math Word Problems Solving with Enhanced Problem-Solution Association
    Zhenwen Liang, Jipeng Zhang and Xiangliang Zhang.
    EMNLP 2022 [Paper]

  • MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving
    Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao and Xiangliang Zhang.
    NAACL 2022 - Findings [Paper, Code]

  • ArMATH: a Dataset for Solving Arabic Math Word Problems
    Reem Alghamdi, Zhenwen Liang and Xiangliang Zhang.
    LREC 2022 [Paper]

  • Data-Efficient Language Shaped Few-shot Image Classification
    Zhenwen Liang and Xiangliang Zhang.
    EMNLP 2021 - Findings [Paper, Code]

  • Explainable and Interpretable Anomaly Detection Models for Production Data
    Basma Alharbi, Zhenwen Liang, Jana M. Aljindan, Ammar K. Agnia and Xiangliang Zhang.
    SPE Journal

  • Solving Math Word Problems with Teacher Supervision
    Zhenwen Liang and Xiangliang Zhang.
    IJCAI 2021​ (acceptance rate of 13.9%, 587/4204) [Paper, Code]

  • Artificial intelligence: The silver bullet for sustainable materials development
    Rifan Hardian, Zhenwen Liang, Xiangliang Zhang, Gyorgy Szekely
    Green Chemistry (IF: 10.2), 2020

  • Traffic sign detection and recognition based on pyramidal convolutional networks
    Zhenwen Liang, Jie Shao, Dongyang Zhang, Lianli Gao
    Neural Computing & Applications, 2020

  • Jointly solving deblurring and super-resolution problems with dual supervised network
    Zhenwen Liang, Jie Shao, Dongyang Zhang
    ICME 2019

Experience

Selected Awards

    AAAI Travel Scholarship, 2023

    National Encouragement scholarship at UESTC, 2018-2019

    National Encouragement scholarship at UESTC, 2017-2018

    Excellent Student Scholarship at UESTC, 2016-2019


© Zhenwen Liang | Last updated: Jan 2025