💡 This blog post is aimed at calling my friends to join with me on topics of uncertainty quantification, fact-checking and detecting machine-generated contents. This research will be carried on at Natural Language Processing department, MBZUAI and Foundation Models Lab, BKAI Research Center.

Research topics

We study reliability and factuality of LLMs with two main thrusts: (1) principled uncertainty quantification (UQ) for multi-step reasoning and agentic systems, and (2) multilingual, culturally-aware fact-checking. The goal is to produce methods, datasets, and open tools that make LLM decisions auditable, efficient, and fair across languages and cultures.

UQ for multi-step reasoning: calibrate step- and chain-level beliefs; propagate uncertainty through tool use/planning; enable selective execution, verification, and test-time scaling under compute budgets.
Data-driven UQ for agentic systems: learn uncertainty from traces/feedback; uncertainty-aware planning and termination; active retrieval/tool calls; budgeted, adaptive decision-making with minimal supervision.
Multilingual & cultural-aware fact-checking: cross-lingual claim normalization and retrieval; culture-specific knowledge grounding; robustness to dialect/code-switching; human-in-the-loop labeling protocols.

Deliverables include open benchmarks, evaluation metrics for step-wise calibration and cross-cultural factuality, and reference implementations deployable in educational and civic-information settings.

What I offer and what I need?

What I need

Have a strong interest in researching in NLP and LLM.
A good background in Math and programming (especially in Python).
Experience in programming machine learning and deep learning algorithms.
A beautiful soul and eager to learn.
No need for prior knowledge of LLM or NLP.

What I have and offer

Access to GPUs for research purpose.
Supports in your own related projects.
A guide of how to do research from A-Z.
Put your name in research publications.
No salary but unlimited funds for iced tea, bubble tea, etc. 😆

Supervisors and Extended Research Team

This research is led by me with the guidance and collaboration from:

Dr. Đinh Viết Sang - Vice Dean of School of ICT and Director of BKAI Research Center, HUST.
Professor Preslav Nakov - Department Chair and Professor of Natural Language Processing, MBZUAI.
Professor Timothy Baldwin - Provost and Professor of NLP, MBZUAI, and Laureate Professor, University of Melbourne.
Dr. Artem Shelmanov - Senior Research Scientist, MBZUAI.
Dr. Yuxia Wang - Assistant Professor, INSAIT in Sofia.
and some students supervised by these professors.

If you are interested in...

Please contact me via my email minh@tnminh.com if you want to work with me or have further questions about this topic.

You can also comment on this blog post for further discussion.

❗️ Deadline for Application: 23:59 15/10/2025.