Knowledge Laboratory (KnOWLab) is a research laboratory run by Natthawut Kertkeidkachorn at the Japan Advanced Institute of Science and Technology (JAIST). Our lab focuses on Natural Language Processing (NLP), Machine Learning and Semantic Web (Knowledge Graphs). We also collaborate closely with the Shirai Lab at JAIST, which specializes in research on Natural Language Processing.

1. Knowledge Generation

• Developing a Knowledge Generation framework to acquire and generate reliable real-world knowledge. Recently, we have focused on how Large Language Models (LLMs) can generate trustworthy knowledge and enhance the explainability of LLMs with Knowledge Graphs.

2. Knowledge-Aware AI Application

• Developing knowledge-aware AI applications, including but not limited to Question Answering, Knowledge Discovery, and Natural Language Understanding across various domains such as Finance and Biomedical Sciences. 

3. Personalization

• Developing personalization applications, including Personal Assistants, User Preference Analysis, and Recommendation Systems, by capturing and integrating human preferences into AI applications. We study various techniques, such as deep learning, prompt engineering, human-in-the-loop, and reinforcement learning.

[8 Mar 2024]: Our paper, in collaboration with the Inoue Lab and the Shirai Lab, received the Best Paper Award at the 30th Annual Meeting of the Association for Natural Language Processing (NLP 2024).

• 井之上直也, 原口大地, 田中健史朗, 白井清昭, Natthawut Kertkeidkachorn, "自己認知は LM as KB の信頼性を高めるか", NLP2024.

[8 Oct 2023]: Our paper, in collaboration with the Inoue Lab and the Shirai Lab, has been accepted in EMNLP 2023 (Findings).

• Daichi Haraguchi, Kiyoaki Shirai, Naoya Inoue, Natthawut Kertkeidkachorn, Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach. EMNLP (Findings), 2023.

[1 Oct 2023]: KnOWLab Kicks off 🎉