Seoyeon Kim

Hello, I am a fourth year M.S. student advised by Prof. Dongha Lee at DLI Lab, Yonsei University.

As a researcher in natural language processing (NLP), I aim to develop a human-like and faithful Large Language Model (LLM). Specifically, my research interest includes: (i) evaluating knowledge of LLMs in various domains and tasks, and (ii) injecting, augmenting, and updating knowledge to LLMs.

Most recently, I am interested in creating benchmarks and evaluating LLMs, especially in terms of their Korean (and multilingual) proficiency on various tasks.


Education
  • Yonsei University
    Yonsei University
    M.S. in Artificial Intelligence
    Sep. 2023 - Aug. 2025 (expected)
  • Yonsei University
    Yonsei University
    B.A. in English Language and Literature
    B.S. in Industrial Engineering
    Mar. 2019 - Aug. 2023
Experience
  • Tutoring
    Tutoring
    AI Researcher
    Mar. 2023 - Feb. 2024
  • Hanwha General Insurance
    Hanwha General Insurance
    AI Engineer Intern
    Jan. 2025 - Feb. 2025
Publications
Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching

Seoyeon Kim, Huiseo Kim, Chanjun Park, Jinyoung Yeo, Dongha Lee

Preprint

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching

Seoyeon Kim, Huiseo Kim, Chanjun Park, Jinyoung Yeo, Dongha Lee

Preprint

VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models

Seoyeon Kim*, Kwangwook Seo*, Hyungjoo Chae, Jinyoung Yeo, Dongha Lee (* equal contribution)

ACL 2024

VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models

Seoyeon Kim*, Kwangwook Seo*, Hyungjoo Chae, Jinyoung Yeo, Dongha Lee (* equal contribution)

ACL 2024

Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement

Hana Kim, Kai Ong, Seoyeon Kim, Dongha Lee, Jinyoung Yeo

EACL 2024

Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement

Hana Kim, Kai Ong, Seoyeon Kim, Dongha Lee, Jinyoung Yeo

EACL 2024