Publications

For the recent publications, please go to my Google Scholar directly.

2025

  1. ACL
    knowledge_cover.png
    Antileak-bench: Preventing data contamination by automatically constructing benchmarks with updated real-world knowledge
    Xiaobao Wu, Liangming Pan, Yuxi Xie, and 7 more authors
    arXiv preprint arXiv:2412.13670, 2025
    PDF
  2. AAAI
    verifiable_cover.png
    Towards Verifiable Text Generation with Generative Agent
    Ji Bin, Liu Huijun, Du Mingzhe, and 5 more authors
    Proceedings of the AAAI Conference on Artificial Intelligence, 2025
    PDF
  3. R2-FM@ICML
    guardreasoner_vl.png
    Guardreasoner-vl: Safeguarding vlms via reinforced reasoning
    Yue Liu, Shengfang Zhai, Mingzhe Du, and 8 more authors
    arXiv preprint arXiv:2505.11049, 2025
    PDF
  4. Preprint
    swe_perf.png
    SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
    Xinyi He, Qian Liu, Mingzhe Du, and 5 more authors
    arXiv preprint arXiv:2507.12415, 2025
    PDF
  5. Preprint
    deceptive_llm.png
    Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
    Zhaomin Wu, Mingzhe Du, See-Kiong Ng, and 1 more author
    arXiv preprint arXiv:2508.06361, 2025
    PDF
  6. PRAL@ICML
    afterburner.png
    Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
    Mingzhe Du, Luu Anh Tuan, Yue Liu, and 6 more authors
    arXiv preprint arXiv:2505.23387, 2025
    PDF
  7. Preprint
    real_world_test.png
    Benchmarking LLMs for Unit Test Generation from Real-World Functions
    Dong Huang, Jie M Zhang, Mark Harman, and 3 more authors
    arXiv preprint arXiv:2508.00408, 2025
    PDF
  8. JMIR
    eraly_maladaptive_schemas.png
    Unraveling Online Mental Health Through the Lens of Early Maladaptive Schemas: AI-Enabled Content Analysis of Online Mental Health Communities
    Beng Heng Ang, Sujatha Das Gollapalli, Mingzhe Du, and 1 more author
    Journal of Medical Internet Research, 2025
    PDF
  9. NeurIPS
    effibench_x.png
    EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
    Yuhao Qing, Boyu Zhu, Mingzhe Du, and 8 more authors
    arXiv preprint arXiv:2505.13004, 2025
    PDF
  10. ICSE
    influence_incorrect_code.png
    Measuring the Influence of Incorrect Code on Test Generation
    Dong Huang, Jie M Zhang, Mark Harman, and 2 more authors
    the International Conference on Software Engineering 2026, 2025
    PDF
  11. NeurIPS
    afterburner.png
    Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
    Mingzhe Du, Luu Anh Tuan, Yue Liu, and 6 more authors
    arXiv preprint arXiv:2505.23387, 2025
    PDF
  12. NeurIPS
    guardreasoner_vl.png
    Guardreasoner-vl: Safeguarding vlms via reinforced reasoning
    Yue Liu, Shengfang Zhai, Mingzhe Du, and 8 more authors
    arXiv preprint arXiv:2505.11049, 2025
    PDF

2024

  1. NeurIPS
    mercury_cover.jpeg
    Mercury: An Efficiency Benchmark for LLM Code Synthesis
    Mingzhe Du, Anh Tuan Luu, Bin Ji, and 2 more authors
    Conference on Neural Information Processing Systems, 2024
    PDF Code Website
  2. ECAI
    health_cover.jpg
    Counseling Responses for Mental Health Forum Questions with Early Maladaptive Schema Prediction
    Das Gollapalli Sujatha, Ang Beng Heng, Du Mingzhe, and 1 more author
    European Conference on Artificial Intelligence, 2024
    PDF Website
  3. arXiv
    test_case_cover.jpg
    Rethinking the Influence of Source Code on Test Case Generation
    Dong Huang, Jie M Zhang, Mingzhe Du, and 2 more authors
    arXiv preprint arXiv:2402.07844, 2024
    PDF
  4. ACL
    arena_cover.jpg
    CodeArena: A Dynamic Evaluation Framework for Code Generation
    Mingzhe Du, Luu Anh Tuan, Ji Bin, and 2 more authors
    arXiv preprint, 2024
    Code
  5. arXiv
    committee_cover.jpg
    Committee:Mitigating Language Model Bias via Weak Supervision
    Mingzhe Du, Anh Tuan Luu, Bingchen Wang, and 2 more authors
    arXiv preprint, 2024
  6. AAAI
    chain_cover.jpg
    Chain-of-Thought Improves Text Generation with Citations in Large Language Models
    Bin Ji, Huijun Liu, Mingzhe Du, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2024
    PDF

2023

  1. TLDK
    constituency_cover.jpeg
    Constituency-Informed and Constituency-Constrained Extractive Question Answering with Heterogeneous Graph Transformer
    Mingzhe Du, Mouad Hakam, See-Kiong Ng, and 1 more author
    In Transactions on Large-Scale Data-and Knowledge-Centered Systems LIII, 2023
  2. WWW
    twitter_cover.png
    Identifying Checkworthy Cure Claims on Twitter
    Sujatha Das Gollapalli, Mingzhe Du, and See-Kiong Ng
    In Proceedings of the ACM Web Conference 2023, 2023
    PDF
  3. AAAI
    aaai23_cover.jpg
    Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse
    Sujatha Das Gollapalli, Mingzhe Du, and See-Kiong Ng
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2023
    PDF Code
  4. AAAI
    dynamind_cover.png
    From Static to Dynamic: A Continual Learning Framework for Large Language Models
    Mingzhe Du, Anh Tuan Luu, Bin Ji, and 1 more author
    arXiv preprint arXiv:2310.14248, 2023
    PDF Code
  5. Openreview
    wave-mechanics.gif
    Debiasing Language Models Using Energy-Guided Ordinary Differential Equations
    Mingzhe Du, Anh Tuan Luu, Bin Ji, and 1 more author
    Openreview id:kaFrlUcAn3, 2023
    PDF Code

2022

  1. CLEF
    checkthat5_cover.png
    NUS-IDS at CheckThat! 2022: identifying check-worthiness of tweets using CheckthaT5
    Du Mingzhe, Gollapalli Sujatha Das, and Ng See-Kiong
    Working Notes of CLEF, 2022
    PDF
  2. arXiv
    image_cover.png
    Image Semantic Relation Generation
    Mingzhe Du
    arXiv preprint arXiv:2210.11253, 2022
    PDF Code