Associate Professor Teeradaj Racharak presented his collaborative research titled “Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning” at the 30th International Conference on Natural Language & Information Systems (NLDB 2025), held in Kanazawa, Japan, from July 4–6, 2025.

This work explores how techniques from software testing can be adapted and applied to evaluate the trustworthiness of large language models (LLMs) in in-context learning settings. The study proposes a framework that systematically generates test cases to identify behavioral inconsistencies and potential failure patterns in LLM responses, contributing to efforts in developing robust, interpretable, and safe natural language systems.

The presentation reflects interdisciplinary collaboration and ongoing research at the Advanced Institute of So-Go-Chi (Convergence Knowledge) Informatics, focusing on trustworthy AI and human-centric language technologies.

Citation:
Teeradaj Racharak, Chaiyong Ragkhitwetsagul, Chommakorn Sontesadisai, Thanwadee Sunetnanta, Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning, In Proceedings of the 30th International Conference on Natural Language & Information Systems (NLDB), Kanazawa, Japan, July 4–6, 2025.