DemoLei
≡
profile photo

Lei (Demo) Wang

I am a Ph.D. student at SMU, where I am fortunate to be advised by Prof. Ee-Peng Lim. I am expected to graduate in May 2024. After graduation, I will be joining Salesforce AI Research in Singapore as a full-time research scientist. My research interests lie at several exciting areas, including math word problem solving, large language models, and recommendation system. Before that, I completed my master's study at UESTC, where I was co-advised by Prof. Dongxiang Zhang and Prof. Xing Xu. My undergraduate studies were also at UESTC, where I earned my bachelor's degree from the school of EE.

Email  /  Google Scholar  /  AGI-Edgerunners  /  GitHub

News

  • 05/2024, I will be joining Salesforce AI Research in Singapore as a full-time research scientist!

  • 03/2024, Our new paper, "Prompt Compression Toolkit", is now available.

  • 03/2024, 1 paper has been accepted to NAACL Findings 2024.

  • 02/2024, Our new paper, "In-Image Learning", is now available.

  • 12/2023, 1 paper has been accepted to AAAI 2024.

  • 10/2023, 5 papers have been accepted to EMNLP 2023.

  • 08/2023, Invited Talk on Large Language Models (LLMs) at CQU. Slides

  • 07/2023, Invited Talk on Large Language Models (LLMs) at NUST. Slides

  • 07/2023, 1 paper has been accepted to ICCV 2023.

  • 05/2023, Invited Talk on Large Language Models (LLMs) at AI Time. Slides

  • 05/2023, 1 paper has been accepted to ACL 2023.

  • 04/2023, 1 paper has been accepted to SIGIR 2023.

  • 03/2023, We have released LLM-Adapters.

  • 11/2022, 2 papers have been accepted to AAAI 2023.

    • Publications

    I'm interested in pushing the boundaries of research in two key areas: large language models and automatic math problem solving.

    Large Language Models

    1. PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models
      Jinyi Li, Yihuai Lan, Lei Wang, Hao Wang
      Preprint 2024 | paper |  

    2. The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation
      Lei Wang, Ee-Peng Lim
      NAACL Findings 2024 | paper | 

    3. All in a Single Image: Large Multimodal Models are In-Image Learners
      Lei Wang, Wanyu Xu, Zhiqiang Hu, Yihuai Lan, Shan Dong, Hao Wang, Roy Ka-Wei Lee, Ee-Peng Lim
      Preprint 2024 | paper |  

    4. Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
      Weijieying Ren, Xinlong Li, Lei Wang, Tianxiang Zhao, Wei Qin
      Preprint 2024 | paper |  

    5. T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering
      Lei Wang, Yi Hu, Jiabang He, Xing Xu, Ning Liu, HUI LIU, Heng Tao Shen
      AAAI 2024 | paper

    6. Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites
      Lei Wang, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim | paper
      MMM 2024

    7. LLM4Vis: Explainable Visualization Recommendation using ChatGPT
      Lei Wang, Songheng Zhang, Yun Wang, Ee-Peng Lim and Yong Wang
      EMNLP Industry 2023 | paper | Oral Presentation (6 out of 77 accepted papers (7.7%)) |  

    8. LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
      Zhiqiang Hu, Lei Wang (corresponding author), Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Roy Ka-Wei Lee, Lidong Bing, Xing Xu, Soujanya Poria
      EMNLP 2023 | paper | Tweeted by AK | Blog by PaperWeekly | 

    9. R^3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context
      Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li, Yunshi Lan
      EMNLP Findings 2023 | paper

    10. Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation
      Yuanyuan Liang, Jianing Wang, Hanlun Zhu, Lei Wang, Yunshi Lan, Weining Qian
      EMNLP 2023 | paper

    11. Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
      Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee and Ee-Peng Lim
      ACL 2023 | paper | Tweeted by AK | AI Daily Paper | 
      We are honored to announce that Plan-and-Solve Prompting has been added to the core library of LangChain, called Plan-and-Execute. Find out what people are saying about it on Twitter.

    12. ICL-D3IE: In-context learning with diverse demonstrations updating for document information extraction
      Jiabang He, Lei Wang (corresponding author), Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen
      ICCV 2023 | paper | 

    13. Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
      Lei Wang, Ee-Peng Lim
      Manuscript 2023 | paper | AI Daily Paper | Blog | 

    14. LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
      Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang
      Manuscript 2023 | 

    15. Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media
      Wei QIN, ZeTong Chen, Lei Wang, Yunshi Lan, Weijieying Ren, Richang Hong
      Manuscript 2023 | paper

    Math Reasoning

      Math Word Problem Solving

    1. Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
      Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, Hen Tao Shen
      EMNLP 2023 | paper | code

    2. Generalizing Math Word Problem Solvers via Solution Diversification
      Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang.
      AAAI 2023 | paper

    3. MWP-BERT: Numeracy-augmented pre-training for math word problem solving
      Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, Xiangliang Zhang.
      NAACL 2022 (Findings) | paper

    4. Mwptoolkit: an open-source framework for deep learning-based math word problem solvers
      Yihuai Lan, Lei Wang (co-first author), Qiyuan Zhang, Yunshi Lan, Bing Tian Dai, Yan Wang, Dongxiang Zhang, Ee-Peng Lim.
      AAAI 2022 (Demo) | paper |  

    5. Improving Compositional Generalization in Math Word Problem Solving
      Yunshi Lan, Lei Wang (corresponding author), Jing Jiang, Ee-Peng Lim.
      MATH-AI at NeurIPS 2022 | paper

    6. Investigating math word problems using pretrained multilingual language models
      Minghuan Tan, Lei Wang, Lingxiao Jiang, Jing Jiang
      MathNLP at EMNLP 2022 | paper

    7. Noahqa: Numerical reasoning with interpretable graph question answering dataset
      Qiyuan Zhang, Lei Wang (co-first author), Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim.
      EMNLP 2021 (Findings) | paper

    8. Teacher-student networks with multiple decoders for solving math word problem
      Jipeng Zhang, Roy Ka-Wei Lee, Ee-Peng Lim, Wei Qin, Lei Wang, Jie Shao, Qianru Sun.
      IJCAI 2020 | paper

    9. Graph-to-tree learning for solving math word problems
      Jipeng Zhang, Lei Wang (co-first author), Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim.
      ACL 2020 | paper

    10. The gap of semantic parsing: A survey on automatic math word problem solvers
      Dongxiang Zhang, Lei Wang (first student author), Luming Zhang, Bing Tian Dai, Heng Tao Shen.
      TPAMI 2019 | paper

    11. Template-based math word problem solvers with recursive neural networks
      Lei Wang, Dongxiang Zhang, Jipeng Zhang, Xing Xu, Lianli Gao, Bing Tian Dai, Heng Tao Shen.
      AAAI 2019 | paper

    12. Modeling intra-relation in math word problems with different functional multi-head attentions
      Jierui Li, Lei Wang (corresponding author), Jipeng Zhang, Yan Wang, Bing Tian Dai, Dongxiang Zhang
      ACL 2019 (Short) | paper

    13. Translating a math word problem to an expression tree
      Lei Wang, Yan Wang, Deng Cai, Dongxiang Zhang, Xiaojiang Liu.
      EMNLP 2018 (Short) | paper

    14. Mathdqn: Solving arithmetic word problems via deep reinforcement learning
      Lei Wang, Dongxiang Zhang, Lianli Gao, Jingkuan Song, Long Guo, Heng Tao Shen.
      AAAI 2018 | paper | Oral Presentation

      Math Word Problem Generation

    15. Math Word Problem Generation via Disentangled Memory Retrieval
      Wei Qin, Xiaowei Wang, Zhenzhen Hu, Lei Wang, Yunshi Lan, Richang Hong
      ACM Transactions on Knowledge Discovery from Data 2024 | paper

    16. Math Word Problem Generation with Memory Retrieval
      Xiaowei Wang, Wei Qin, Zhenzhen Hu, Lei Wang, Yunshi Lan, Richang Hong
      PRCV 2022 | paper

    Recommendation

    1. Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective
      Weijieying Ren, Lei Wang (co-first author), Kunpeng Liu, Ruocheng Guo, Lim Ee Peng, Yanjie Fu.
      ICDM 2022 | paper

    2. Explanation guided contrastive learning for sequential recommendation
      Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao.
      CIKM 2022 | paper

    3. Next-term grade prediction: A machine learning approach
      Audrey Tedja Widjaja, Lei Wang,, Nghia TRUONG TRONG, Aldy Gunawan, Ee-Peng Lim.
      EDM 2020 | paper

    Multimodal Scenarios

    1. Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models
      Jiabang He, Yi Hu, Lei Wang (corresponding author), Xing Xu, Ning Liu, Hui Liu and Heng Tao Shen.
      SIGIR 2023 | paper | code

    2. Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models
      Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu
      AAAI 2023 | paper | code | Oral Presentation

    Others

    1. Gradient-Aware Logit Adjustment Loss for Long-Tailed Classifier
      Fan Zhang, Wei Qin, Weijieying Ren, Lei Wang, Zetong Chen, Richang Hong
      ICASSP 2024 | paper

    2. FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation
      Hanyue Du, Yike Zhao, Qingyuan Tian, Jiani Wang, Lei Wang, Yunshi Lan and Xuesong Lu
      CIKM Resource 2023 | paper | Code and Dataset: Coming Soon.

    3. A Prompt-Based Topic-Modeling Method for Depression Detection on Low-Resource Data
      Yanrong Guo, Jilong Liu, Lei Wang, Wei Qin, Shijie Hao, Richang Hong
      IEEE Transactions on Computational Social Systems 2023 | paper

    4. Deepstyle: User style embedding for authorship attribution of short texts
      Zhiqiang Hu, Roy Ka-Wei Lee, Lei Wang, Ee-peng Lim, Bo Dai.
      APWeb-WAIM 2020 | paper

    5. CRAN: a hybrid CNN-RNN attention-based model for text classification
      Long Guo, Dongxiang Zhang, Lei Wang, Han Wang, Bin Cui
      Conceptual Modeling 2018 | paper

    Awards

  • Presidential Fellowship, 2023.07-2023.12

  • Presidential Fellowship, 2020.01-2022.07

  • Excellent Master Thesis Award, 2019

  • National Scholarship for Graduate Students, 2018

  • The First Prize Scholarship, 2018

  • Outstanding Student Award, 2018

    • Student Collaboration/Mentoring

  • Zhiqiang Hu (2019-Current), UESTC -> PhD at SUTD

  • Yihuai Lan (2021-Current), Xihua -> RA at HKUST (Guangzhou)

  • Wanyu Xu (2022-Current), Xihua -> master student at SWJTU

  • Jiabang He (2021-2023), UESTC -> Huawei

  • Qiyuan Zhang (2019-2021), UESTC -> PhD at CityU

  • Jipeng Zhang (2018-2020), UESTC -> PhD at HKUST

  • Jierui Li (2018-2019), UESTC -> PhD at UT Austin

    • We refer to Yunhe Wang's website source code. Please find my source code here.