Publications / Preprints

* denotes Equal Contribution

Please see my Google Scholar for the most up-to-date list of publications.

2026

  1. preprint
    TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding
    Quynh Vo, Cong-Duy Nguyen, Ponhvoan Srey, and 2 more authors
    arXiv preprint arXiv:2607.11131, 2026
  2. preprint
    From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
    Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen, and 3 more authors
    arXiv preprint arXiv:2606.27679, 2026
  3. EMNLP Findings
    Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
    Vu Duc Anh, Nhat M Hoang, Do Xuan Long, and 3 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026
  4. EMNLP Findings
    Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
    Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu, and 1 more author
    In Findings of the Association for Computational Linguistics: EMNLP, 2026
  5. ACL
    Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
    Ponhvoan Srey, Xiaobao Wu, Cong-Duy T Nguyen, and 1 more author
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

2025

  1. EMNLP
    Unsupervised Hallucination Detection by Inspecting Reasoning Processes
    Ponhvoan Srey, Xiaobao Wu, and Anh Tuan Luu
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025
  2. MLJ
    Uncover and unlearn nuisances: agnostic fully test-time adaptation
    Ponhvoan Srey*, Yaxin Shi*, Hangwei Qian, and 2 more authors
    Machine Learning, 2025

2024

  1. CAI
    Open-world learning under dataset shift
    Ponhvoan Srey, Yuhui Zhang, and Takafumi Kanamori
    In 2024 IEEE Conference on Artificial Intelligence (CAI), 2024