Tran Phuoc Thanh Nhan | NLP & AI Researcher

University of Information Technology - Vietnam National University Ho Chi Minh City.

profile.jpg

Hi, I am Tran Phuoc Thanh Nhan, a dedicated Computer Science Undergraduate Researcher at the University of Information Technology (UIT), Vietnam National University. Fueled by a long-standing passion for mathematics and algorithmic problem-solving, I maintain an excellent academic record at UIT, with grades consistently at the excellence level as a Top 6% academic scholarship recipient. Currently, I balance my academic pursuits as an Undergraduate Research Assistant under the supervision of Dr. Dang Van Thin, and my leadership experience serving as the Head of AI Team (Gen 6) at Google Developer Group (GDG) on Campus - UIT.

Focus

My current work revolves around building reliable and practical AI systems. I focus on:

  • Natural Language Processing (NLP) & Generative AI
  • Retrieval-Augmented Generation (RAG)
  • Multi-Agent Systems
  • Large Language Model (LLM) fine-tuning (e.g., LoRA)



Highlighted Work

Bridging the gap between academic theory and practical software engineering, I architect impactful systems:

  1. AskUIT AI Academic Assistant: An intelligent chatbot that won the Encouragement Prize at SEApp 2025. This project leverages a Multi-Agent architecture and a Hybrid Search RAG pipeline to deliver university-specific academic support.
  2. Competitive Programming Repository: My long-standing algorithm collection (150+ highly optimized solutions across Codeforces, CSES, VNOI). It demonstrates my deep foundation in discrete math and high-performance C++.

news

Sep 18, 2026 Paper published at MAPR 2026: Retrieval-Augmented Fine-Tuning with Reasoning Distillation for Vietnamese Medical Question Answering (with Huynh Nguyen Phu, Truong Quoc Truong, and Dang Van Thin). The paper proposes a retrieval-augmented fine-tuning (RAFT) pipeline for Vietnamese medical QA that distills Chain-of-Thought rationales from a large language model into LLaMA-3-8B via Low-Rank Adaptation (LoRA). Using oracle-and-distractor contexts built from VMHQA and a fixed oracle-context protocol for retrieval-independent evaluation, the fine-tuned model reaches 93.64% accuracy and 93.56% macro-F1, outperforming both the provided-context baseline and zero-shot LLaMA-3-70B while remaining competitive with prior VMHQA results including fine-tuned GPT-4o.
Jul 01, 2026 Paper accepted at SemEval-2026 Task 9: Gradient Descenders at SemEval-2026 Task 9: Data-Centric Counterfactual Augmentation for Multi-Label Hate Speech Detection (with Dang Van Thin). The work addresses multi-label hate speech detection by introducing a data-centric counterfactual augmentation strategy that generates targeted training perturbations. The approach improved robustness and generalization in the shared task evaluation, with findings presented at the 20th International Workshop on Semantic Evaluation (ACL).
Jun 15, 2026 Paper accepted at DeSegMa-IT: Gradient Descenders at DeSegMa-IT: Leveraging Monolingual Transformer for LLM-Generated Text Detection and Boundary Identification (with Bui Hong Son and Dang Van Thin). The paper tackles detection of LLM-generated text by leveraging a monolingual Transformer, jointly addressing classification and boundary identification of machine-written spans. The approach was evaluated within the DeSegMa-IT shared task at the International Workshop on Evaluation of Natural Language and Speech Tools for Italian.

latest posts

selected publications

  1. brownian-motion.gif
    Gradient Descenders at SemEval-2026 Task 9: Data-Centric Counterfactual Augmentation for Multi-Label Hate Speech Detection
    Tran Phuoc Thanh Nhan and Dang Van Thin
    In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), Jul 2026
  2. wave-mechanics.gif
    Gradient Descenders at DeSegMa-IT: Leveraging Monolingual Transformer for LLM-Generated Text Detection and Boundary Identification
    Tran Phuoc Thanh Nhan, Bui Hong Son, and Dang Van Thin
    In International Workshop on Evaluation of Natural Language and Speech Tools for Italian, Feb 2026
  3. Retrieval-Augmented Fine-Tuning with Reasoning Distillation for Vietnamese Medical Question Answering
    Tran Phuoc Thanh Nhan, Nguyen Phu Huynh, Truong Quoc Truong, and 1 more author
    In 2026 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), Aug 2026