Tin Nguyen

I'm Tin Nguyen, currently pursuing my PhD in AI at Auburn University with Anh Totti Nguyen.
I am exploring explainable, editable machine learning approaches, though my interests extend beyond these areas.
Feel free to chat with me via ngthanhtinqn@gmail.com or ttn0011@auburn.edu

CV  /  Google Scholar  /  ResearchGate  /  Twitter  /  Github

Latest News  /  Feature Projects

Large Language Models (LLMs) sometimes generate non-factual statements. To address this, the Highlighted Chain-of-Thought Prompting (HoT) technique was developed, enhancing responses by marking key facts with XML tags in both the query and the response. HoT improves upon traditional prompting methods in few-shot settings across various tasks, helping users more accurately identify correct LLM responses. However, it also increases the likelihood of users mistakenly accepting incorrect answers as correct.

We proposed a part-based bird classifier that makes predictions based on part-wise descriptions. Our method directly utilizes human-provided descriptions (in this work, from GPT4). It outperforms CLIP and M&V by 10 points in CUB and 28 points in NABirds.

This study proposes a coarse-to-fine fusion module between vision and language. This will help an agent learn a joint representation while navigating in a virtual environment.

• EMNLP, ACL (Top Conference in NLP)
• Knowledge-based Systems (Q1 Journal)