Manh Nguyen

PhD Student @ Applied Artificial Intelligence Initiative

prof_pic.jpg

Hello, my name is Manh (Mạnh in Vietnamese). I am pursuing my PhD journey under the supervision of Dr. Hung Le and Prof. Sunil Gupta at A2I2, Deakin University. My thesis, “Towards Reliable Large Language Models for Open-ended Question Answering”, aims to explore how we can build more trustworthy AI systems that can handle open-ended questions effectively. Prior to my PhD, I spent five years applying machine learning to solve real-world data science challenges in industry.

I focus on practical NLP research, building robust and scalable systems that translate research ideas into real-world impact.

news

Apr 07, 2026 One paper, titled “SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning” has been accepted to ACL 2026 (Findings).
Nov 08, 2025 My first PhD paper, titled “Probabilities Are All You Need: A PRobability-Only Approach to Uncertainty Estimation in Large Language Models” has been accepted to AAAI 2026.
Sep 09, 2025 PhD confirmation outcome deemed satisfactory.
Apr 06, 2025 One paper, titled “Topic classification of vietnamese product reviews in e-commerce using PhoBERT” has been accepted to Journal of Marketing Analytics (Q1).
Oct 28, 2024 Commenced my PhD journey at A2I2, Deakin University, Australia.

selected papers

  1. UAB (preprint)
    uab_logo.svg
    Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
    Manh Nguyen, Sunil Gupta, and Hung Le
    2026
  2. RCS (preprint)
    rcs_logo.svg
    Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score
    Manh Nguyen, Sunil Gupta, and Hung Le
    2026
  3. DAR (preprint)
    darlogo.webp
    Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
    Manh Nguyen, Anh Nguyen, Dung Nguyen, and 2 more authors
    2026
  4. GRAD (preprint)
    grad_logo.svg
    GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation
    Manh Nguyen, Sunil Gupta, Dai Do, and 1 more author
    2025
  5. PRO (AAAI-26)
    pro_logo.svg
    Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models
    Manh Nguyen, Sunil Gupta, and Hung Le
    The 40th Annual AAAI Conference on Artificial Intelligence, 2026