Jiho Kim

Google Scholar  /  Twitter  /  Github

jiho.kim at kaist.ac.kr

I am a Ph.D. student at Edlab @ KAIST AI, advised by professor Edward Choi. I also work closely with professor Yohan Jo at Seoul National University. My research focuses on evaluating and enhancing Large Language Model (LLM)-based agents. A key aspect of my work is improving these agents' reasoning abilities, especially in reasoning over knowledge graphs. Additionally, I am actively evaluating the performance of LLM agents in real-world applications, which has led me to create a dialogue simulator for assessing conversational agents. I am currently expanding this simulator to explore agent personalization within simulated environments.

I am also passionate about applying AI-driven advancements in the healthcare domain. By improving the reasoning and personalization of AI agents, I aim to enhance diagnostic processes, patient care, and overall healthcare outcomes.

  1. Large Language Model: Arxiv'24, NeurIPS'24, EMNLP'23

  2. Knowledge Graph: Arxiv'24, ACL'23, EMNLP'23, CHIL'22

  3. Fact Verification: NeurIPS'24, ACL'23, EMNLP'23

  4. Healthcare: NeurIPS'24, ICASSP'23, JAAD'23, CHIL'22, ML4H'21

* denotes equal contribution

KoSAIM Summer School - Numpy and Pytorch Intro Hands-on session (Aug 2023)

KAIST — Lecture Series on "ChatGPT & Applications" at KOOC & KAIST IT Academy (June 2023)

KAIST - Teaching Assistant, Programming for AI (Fall 2021)

M.S. & Ph.D. integrated course in KAIST AI, Aug. 2021 - present (advisor: Prof. Edward Choi)

B.S. in Electrical Engineering and Computer Science (minored), KAIST, Mar. 2017 - Aug. 2021

Conference Reviewer: EMNLP 2023, ARR (2024 Feb, 2024 April, 2024 June, 2024 Oct), COLM 2024, ICLR 2025

Journal Reviewer: ACM Health, ACM TOIS