profile photo

Jiho Kim

Google Scholar  /  Twitter  /  Github

jiho.kim at kaist.ac.kr

About

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.

Topics of interest

  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

Publications

* denotes equal contribution

DialSim: A Real-Time Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents
Jiho Kim, Woosog Chay, Hyeonji Hwang, Daeun Kyung, Hyunseung Chung, Eunbyeol Cho, Yohan Jo, Edward Choi
Preprint

EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
Yeonsu Kwon*, Jiho Kim*, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi
NeurIPS 2024 Datasets and Benchmarks
Spotlight Presentation
NeurIPS 2024 Financial Aid Award

KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
Jiho Kim, Yeonsu Kwon, Yohan Jo, Edward Choi
EMNLP 2023 Findings

FactKG: Fact Verification via Reasoning on Knowledge Graphs
Jiho Kim, Sungjin Park, Yeonsu Kwon, Yohan Jo, James Thorne, Edward Choi
ACL 2023

Text-To-ECG: 12-Lead Electrocardiogram Synthesis Conditioned on Clinical Text Reports
Hyunseung Chung, Jiho Kim, Joon-myoung Kwon, Ki-Hyun Jeon, Min Sung Lee, Edward Choi
ICASSP 2023

Measurement of psoriasis-affected area with artificial neural network
Woo Hyup Lee, Sungmin Lee, Jiho Kim, Ju Hee Han, Yeong Ho Kim, Junhwi Kim, Ji Hyun Lee, Chul Hwan Bang
JAAD 2023 (Impact Factor: 15.487)

Graph-Text Multi-Modal Pre-training for Medical Representation Learning
Sungjin Park, Seongsu Bae, Jiho Kim, Tackeun Kim, Edward Choi
CHIL 2022

Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture
Seongsu Bae, Daeyoung Kim, Jiho Kim, Edward Choi
ML4H 2021
Oral Spotlight
Lectures & Teaching

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)

Education

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

Academic Activities

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

Journal Reviewer: ACM Health, ACM TOIS

The template is from this website.