📧 [email protected] | [email protected] | 🌐 Personal Website | 💻 GitHub

Monash University
Starting May 2025

MISA JSC - misa.vn
January 2025 - May 2025

• Built top-ranked Vietnamese LLMs (VMLU #1 as of March 25, 2025; government-organized national top 5)
• Built automated data generation and evaluation tools, local LLMs and domain experts (Accounting, Finance Analysis)
• Focus: LLM fine-tuning and alignment, safety alignment, RAG, agent and multi-agent chatbots.

MISA JSC - misa.vn
April 2024 - December 2024

• Developed Legal document Q&A chatbot (search accuracy >95%, answer accuracy >90% accuracy on 1000+ expert-curated real-world questions, 1000+ documents each 3-300 pages long)
• Focus: Rasa, databases, chunking, RAG, text2sql, LLMs.

VinAI Research - vinai.io
March 2022 - April 2024

• Supervisor: Asst. Prof. Thien Huu Nguyen
• Research Topic: Weakly supervised learning, Information Extraction

• SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning
  Thanh-Thien Le, Viet Dao*, Linh Văn Nguyen*, Thi-Nhung Nguyen, Linh Van Ngo, Thien Huu Nguyen*
  2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)

• BKEE: Pioneering Event Extraction in the Vietnamese Language
  Thi-Nhung Nguyen, Bang Tran, Trong-Nghia Luu, Kiem-Hieu Nguyen and Thien Huu Nguyen
  The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

• A Self-enhancement Multitask for Unsupervised Aspect Category Detection
  Thi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, Tuan-Dung Cao
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023

• An Uncertainty-aware encoder for Aspect Detection
  Thi-Nhung Nguyen, Kiem-Hieu Nguyen, Young-In Song, Tuan-Dung Cao
  Findings of the Association for Computational Linguistics: EMNLP 2021

VinAI Research
March - August 2023

• Supervisor: Dr. Dat Quoc Nguyen
• Research Topic: LLM from scratch, Crawling, Ranking models, LLMs

• Programming Languages: Python, SQL
• Libraries & Frameworks: PyTorch, Rasa, FastAPI, LangGraph, ...
• AI & ML Technologies: LLMs, RAG, Embedding Models, Text2SQL, LLMs Finetuning and Alignment, Reinforcement Learning
• Databases & Search: MongoDB, SQLite, Elasticsearch, Qdrant, Hybrid Search
• Cloud Technologies: AWS, Azure
• DevOps & CI/CD: Docker, Jenkins
• Developer Tools: Git, GitHub, GitLab, Jira, VS Code
• Leadership & Management: Agile, Scrum, Team Mentorship, Project Management, Stakeholder Communication