Eunseong Choi

Eunseong Choi (최은성)

I am a Research Scientist at Liner, working on helping people get smarter faster. I received my Ph.D. from DIAL Lab at Sungkyunkwan University, advised by Prof. Jongwuk Lee. My research lies in Information Retrieval (IR) and Natural Language Processing (NLP), with a focus on building robust and efficient Retrieval-Augmented Generation (RAG) frameworks. In particular, I study context–memory conflicts, prompt compression, and passage re-ranking.

Keywords: Retrieval-Augmented Generation, Efficient LLMs, Information Retrieval, NLP

Work Experience

ML Research Scientist, Core Tech Division
Liner, Seoul, Republic of Korea
Dec 2025 – Present
  • Trained and deployed a neural re-ranker, improving retrieval performance by 12.5% over the previous production model
  • Built a daily incremental pipeline to improve search index freshness
Research Intern, Search & Ranking Modeling
NAVER Corp., Seongnam-si, Gyeonggi, Republic of Korea
Mar 2025 – Apr 2025

Focus: Continual fine-tuning for recency-aware dense retrieval

Research Intern, Search CIC
NAVER Corp., Seongnam-si, Gyeonggi, Republic of Korea
Jul 2021 – Aug 2021

Focus: Sparse retrieval method for efficient first-stage retrieval

Education

M.S./Ph.D., Artificial Intelligence
Sungkyunkwan University
Mar 2020 – Feb 2026

Advisor: Prof. Jongwuk Lee

Thesis: Improving Evidentiality and Compression for Retrieval-Augmented Generation

B.S., Architecture
Sungkyunkwan University
Mar 2012 – Feb 2020

B.S., Samsung Convergence Software Course

Publications

Under Review

International Conferences

Domestic Journals & Conferences

Talks

From Research to Production in Agentic RAG
Invited Talk, Korea Information Processing Society (KIPS)
From IR to RAG: When Search Meets AI
Guest Lecture, Big Data Mining Course, Hankuk University of Foreign Studies
Jun 9, 2026

Honors & Awards