NLP Lab

Natural Language Processing

UNIST 자연어처리 연구실은 인간이 지식을 확장하고 습득하는 과정을 모사하여, 지식의 점진적 학습과 조작 능력을 갖춘 일반 언어지능(AGLI)을 구현하기 위한 System 2 기반 언어 AI를 연구합니다.

인간 수준의 지식 학습과 추론 능력을 갖춘 차세대 언어 AI를 연구하며, 대학원생 및 연구원을 모집하고 있습니다.

The Natural Language Processing Lab at UNIST develops System 2-based language AI that simulates how humans expand and acquire knowledge, striving toward Artificial General Language Intelligence (AGLI) with progressive knowledge learning and manipulation.

We advance next-generation language AI with human-level knowledge learning and reasoning capabilities. We are recruiting graduate students and researchers.

UNIST 인공지능대학원 자연어처리 연구실 Natural Language Processing Lab, UNIST
울산광역시 울주군 유니스트길 50, 106동 807A 50 UNIST-gil, Ulju-gun, Ulsan 44919, Republic of Korea · Bldg. 106, Rm. 807A

최근 소식 Recent News Recent News

전체보기 → View all →
  • Prof. Na will serve as an Area Chair for NeurIPS 2026
  • Three papers are accepted in ACL 2026 (3 Findings)
  • One paper is accepted in Expert Systems with Applications
  • One paper is accepted in CVPR 2026 (1 Findings)
  • One paper is accepted in TACL
  • One paper is accepted in ICLR 2026
  • One paper is accepted in Expert Systems with Applications
  • One paper is accepted in EMNLP 2025 (1 Findings)

주요 논문 Selected Publications Selected Publications

전체보기 → View all →
  1. PRIME: Ultra-Low-Rank Principal-Residual Model MergingACL 2026 FindingsSeung-Ho Lee, Kyungsu Lee, BAZARVAANI ZUCHI, Jeongmin Ahn, Insuk Seo, Donghyeon Jeon, Inho Kang, Seung-Hoon Na
  2. PURE: Post-hoc Unlocking and REfinement for Discrete Diffusion DecodingACL 2026 FindingsYangryeol Park, Kunhui Lee, Hanback Choi, Cheoneum Park, Donghyeon Jeon, Inho Kang, Seung-Hoon Na
  3. EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge EditingACL 2026 FindingsJungyu Lee, Kunhui Lee, Gyun Lee, Seung-Hoon Na
  4. AlphaMerging: Orthogonal Subspace Projection of Task Vectors to Reduce Task Interference for Multi-Task Model MergingCVPR 2026 FindingsBAZARVAANI ZUCHI, Seung-Ho Lee, Ahn Jeongmin, Donghyeon Jeon, Inho Kang, Seung-Hoon Na
  5. GateLM: Jointly Injecting Knowledge Graphs and Texts for Reasoning-Enhanced Language Models on Commonsense Question AnsweringExpert Systems With Applications 2026Jinwoo Min, Kun-Hui Lee, Roseline Nyange, Seung-Hoon Na
  6. OrthoEdit: Principled and Stable Knowledge Editing via Orthogonal Subspace ProjectionTACL 2026 (accepted)Shanbao Qiao, Xuebing Liu, Akshat Gupta, Seung Hoon Na
  7. MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAGICLR 2026Xuebing Liu, Shanbao Qiao, Roseline Nyange, Dongwook Min, Hyun Kim, Seung Hoon Na
  8. MECA: Modular Editing via Customized Expert Networks and Adaptors in Large Language ModelsExpert Systems with Applications 2025Roseline Nyangea, Shanbao Qiao, Seung Hoon Na
  9. GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMsEMNLP Findings 2025Xuebing Liu, Shanbao Qiao and Seung-Hoon Na
  10. Optimizing Causality-Based Radiology Reporting with Retrieval-Augmented and Structured Reasoning Approaches for the NTCIR-18 HIDDEN-RAD TaskNTCIR-18 2025Ju-Min Cho, Ho-Jin Yi, Myung-Kyu Kim and Seung-Hoon Na [PDF]

박사후연구원 Postdoctoral Researcher Postdoctoral Researcher InnoCORE

nash@unist.ac.kr →
InnoCORE · NLP & LLM Research

UNIST 자연어처리 연구실은 현재 InnoCORE 박사후연구원 프로그램(연봉: 최대 5년간 연 9천만 원)을 통해 박사후연구원을 모집하고 있습니다.

자연어처리, 머신러닝, 인공지능, 컴퓨터과학, 수학, 물리학 또는 관련 분야 배경을 가진 지원자를 환영합니다. 지원자는 자연어처리(NLP), 대규모 언어모델(LLMs), 추론, 검색증강생성(RAG), 지식 편집, 모델 병합, 확산 언어모델, 멀티 에이전트 시스템, 지식 증류 또는 관련 머신러닝 연구 분야 중 하나 이상에서 우수한 연구 실적과 전문성을 갖추고 있기를 강하게 기대합니다.

해당 포지션은 2026년 여름부터 즉시 시작 가능합니다.

Our NLP Lab at UNIST is currently recruiting Postdoctoral Researchers through the InnoCORE Postdoctoral Program (salary: 90 million KRW per year for up to 5 years).

We welcome applicants with backgrounds in Natural Language Processing, Machine Learning, Artificial Intelligence, Computer Science, Mathematics, Physics, or related fields. We strongly expect candidates to have a strong research record and expertise in one or more of the following areas: Natural Language Processing (NLP), Large Language Models (LLMs), reasoning, Retrieval-Augmented Generation (RAG), knowledge editing, model merging, diffusion language models, multi-agent systems, knowledge distillation, or related machine learning research areas.

The position is available to start immediately from Summer 2026.

연구 방향 Research Research Overview

전체보기 → View all →

Our NLP lab at UNIST eventually aims to develop a System 2-based language AI that simulates how humans expand and acquire knowledge, ultimately striving to build an Artificial General Language Intelligence (AGLI) intensively equipped with progressive knowledge learning and manipulation capabilities.

Given this aim, our research goes beyond System 1 abilities focused on short-term factual recall and aims to endow large language models (LLMs) with System 2-level cognitive skills-such as long-term learning, conceptual understanding, and creative knowledge composition.

Particularly, noting that current LLMs are remarkable but still remain inefficient at knowledge injection and manipulation and fall qualitatively short of human-level capabilities, our current interests include:

UNIST 자연어처리 연구실은 인간이 지식을 확장하고 습득하는 과정을 모사하여 지식 점진적 학습 및 조작 능력을 갖춘 일반 언어지능(Artificial General Language Intelligence, AGLI)을 구현하기 위한 System 2 기반 언어 AI 연구를 목표로 합니다.

본 연구실은 단기적 사실 회상 중심의 System 1 능력을 넘어, System 2 수준의 고차원적 추론 능력—즉 장기 학습, 개념 이해, 창의적 지식 조합—을 대규모 언어모델(LLM)에 부여하는 것을 연구하고 있습니다.

현재의 LLM이 뛰어난 성능에도 불구하고 지식 주입 및 조작(knowledge injection and manipulation)에서 여전히 비효율적이라는 인식하에, 연구실은 다음 분야를 중점적으로 다루고 있습니다:

  1. Editing and leveraging knowledge in unstructured text비정형 텍스트 상의 지식 편집 및 활용
  2. Efficient reasoning based on knowledge learning지식 학습 기반의 효율적 추론
  3. Integrating external memory with parameter-efficient LLMs외부 메모리와 파라미터 효율형 LLM의 통합
  4. Progressive knowledge expansion via Mixture-of-Experts (MoE)Mixture-of-Experts(MoE)를 통한 점진적 지식 확장
NLP LLM RAG Mixture-of-Experts Knowledge Editing Diffusion LM Model Merging Agentic AI

In the mid-term, the lab also aims to develop parametric equivalents of in-context knowledge editing. In the long-term, we seek mechanisms for long-term conceptual learning, ultimately enabling LLM agents to master knowledge at a human level. Overall, we are dedicated to establishing foundational technologies that will drive next-generation language intelligence.

중기적으로는 In-context 지식 편집의 파라미터적 등가 모델 개발을, 장기적으로는 장기 지식 및 개념 학습 메커니즘을 완성하여 인간 수준의 지식 숙달 능력을 갖춘 LLM 에이전트를 구현하는 것을 목표로 합니다. 이를 통해 차세대 언어지능을 위한 원천 기술 확보에 주력하고 있습니다.

Introduction

  • Introduction to the Natural Language Processing Lab [pdf]자연어처리 연구실 소개 [pdf]

Announcement

We are now recruiting graduate students or researchers. If you are interested in joining our lab, please send me an email that describes your interests and experience (including CV)!

저희 연구실에서는 현재 대학원생 및 연구원을 모집하고 있습니다. 관심 있는 분께서는 본인의 연구 관심 분야와 경력(이력서 포함)을 소개하는 이메일을 보내주시기 바랍니다.

  • Admission Guides for International Students (Graduate School) are announced. Please refer to the board in School homepage.(대학원) 입학 안내가 공지되었습니다. 자세한 내용은 학교 홈페이지를 참고하시기 바랍니다.

Courses

Courses →

UNIST울산과학기술원

  • 자연어처리Natural Language Processing - CSE40201 - 2026 1학기- CSE40201 - 2026 1st semester
  • 딥러닝 원론Principles of Deep Learning - AI50201 - 2025 2학기- AI50201 - 2025 2nd semester
  • 자연어처리Natural Language Processing - CSE40201 - 2025 1학기- CSE40201 - 2025 1st semester
Join Us

함께 연구할 대학원생과 연구원을 찾습니다 We are recruiting graduate students and researchers

대학원생 · 연구원Graduate Students & Researchers

우리 연구실은 대학원생과 연구원을 모집하고 있습니다. 함께 연구하고 싶은 분은 관심 분야와 경험(CV 포함)을 담아 이메일로 연락 바랍니다.

We are recruiting graduate students and researchers. If you are interested in joining our lab, please email us describing your interests and experience, including a CV.

nash@unist.ac.kr →