Domestic Conferences

[D18] 시각-언어 모델 생성 설명문을 활용한 하이브리드 문서 검색
(Hybrid Document Retrieval with VLM-Generated Descriptions)

• Ho Seob Ahn, Mingyu Kim, Taeuk Kim [Outstanding Paper Award (우수논문상)]

• Korea Computer Congress 2026 (KCC 2026)

[D17] 내부 표현 비교를 통한 LLM 언러닝 평가
(Evaluating LLM Unlearning via Comparison of Internal Representations)

• Ingyu Bang, Hwiyeong Lee, Hyelim Lim, Hoki Kim, Taeuk Kim

• Korea Computer Congress 2026 (KCC 2026)

[D16] 한국어 LLM-as-a-Judge를 위한 루브릭 전략 비교
(Comparison of Rubric Strategies for LLM-as-a-Judge in Korean)

• Minseo Kim, Yukyung Lee, Taeuk Kim

• Korea Computer Congress 2026 (KCC 2026)

[D15] LLM 내부 지식 분석을 위한 표현 단위 비교: Neurons vs. SAEs
(Representation Units for LLM Knowledge Analysis: Neurons vs. SAEs)

• Hyelim Lim, Ingyu Bang, Hwiyeong Lee, Taeuk Kim

• Korea Computer Congress 2026 (KCC 2026)

[D14] LLM 추론 과정의 인식적 신호를 활용한 신뢰도 추정
(Confidence Estimation from Epistemic Signals in LLM Reasoning Traces)

• Ki Jung Seo, Taeuk Kim

• KIIS Spring Conference 2026 (KIIS 2026)

[D13]  거대 언어 모델 관용구 처리의 역전의 저주 현상 탐구
(Reversal Curse in Idiomatic Tasks of Large Language Models)

• Jisu Kim, Taeuk Kim

• Korea Software Congress 2025 (KSC 2025)

[D12] 대화 맥락 추론 향상을 위한 리즈닝 피드백 기반 학습
(Enhancing Conversational Context Inference via Reasoning Feedback-Based Learning)

• Yuri Son, Taeuk Kim

• The 37th Annual Conference on Human and Cognitive Language Technology (HCLT 2025)

[D11] 한국어 표 설명 능력 향상을 위한 전처리 및 학습 방법론 탐구
(Learning Strategies to Improve Table Understanding and Explanation in Korean)

• Changhyeon Kim, Seunghee Kim, Taeuk Kim

• The 36th Annual Conference on Human and Cognitive Language Technology (HCLT 2024)  [Best Paper Award (최우수논문상)]

[D10] KR-HumanEval을 활용한 언어 모델의 한국어 프로그램 합성 성능 분석
(Analysis of Language Models in Korean Program Synthesis Based on the KR-HumanEval Benchmark)

• Deokyeong Kang, Taeuk Kim

• The 36th Annual Conference on Human and Cognitive Language Technology (HCLT 2024)  [Best Paper Award (최우수논문상)]

[D9] 한국어 발화의 다중 의도 감지 연구
(Multi-Intent Detection for Korean Spoken Language)

• Yejin Yoon*, Jisu Kim*, Jungmin Im, Jungyeon Lee, Taeuk Kim (*: equal contribution)

• Korea Computer Congress 2024 (KCC 2024) [Outstanding Paper Award (우수논문상)]

[D8] 다중 레이블 분류를 위한 프롬프팅 고도화
(Enhanced Prompting for Multi-Label Classification)

• Jungyeon Lee, Youngwoo Shin, Yejin Yoon, Taeuk Kim

• Korea Computer Congress 2024 (KCC 2024)

[D7] 생락과 상호참조를 보강한 다중 의도 데이터셋
(A Multi-Intent Dataset Enhanced with Implicit Concatenation)

• Sungmin So*, Jiwoo Min*, Yejin Yoon, Jungyeon Lee, Taeuk Kim (*: equal contribution)

• Korea Computer Congress 2024 (KCC 2024)

[D6] 기계 독해를 활용한 한국어 의미역 결정
(Korean Semantic Role Labeling with Machine Reading Comprehension)

• Kang Min Lee, Dong Geon Seo, Eunrang Kwon, Junmo Song, Jeonghan Kang, Taeuk Kim 

• Korea Computer Congress 2024 (KCC 2024)

[D5] 대조학습 기반 문장표현 방법론 개선을 위한 공통 오류 분석 및 앙상블 기법
(Enhancing Sentence Representations with Common Error Analysis and Ensemble Techniques in Contrastive Learning)

• Jii Cha, Taeuk Kim

• Korea Software Congress 2023 (KSC 2023)

[D4] 효과적인 한국어 교차언어 전송을 위한 특성 연구
(Research on Features for Effective Cross-Lingual Transfer in Korean)

• Taejun Yun, Taeuk Kim

• The 35th Annual Conference on Human and Cognitive Language Technology (HCLT 2023)

[D3] MAdapter: 효율적인 중간 층 도입을 통한 Adapter 구조 개선
(MAdapter: A Refinement of Adapters by Augmenting Efficient Middle Layers)

• Jinhyeon Kim, Taeuk Kim

• The 35th Annual Conference on Human and Cognitive Language Technology (HCLT 2023)

[D2] 원천 언어 다각화를 통한 교차 언어 전이 성능 향상
(Enhanced Zero-Shot Cross-Lingual Transfer with the Diversification of Source Languages)

• Seong Hoon Lim, Taeuk Kim

• Korea Computer Congress 2023 (KCC 2023)

[D1] 한국어 문장 표현을 위한 비지도 대조 학습 방법론의 비교 및 분석
(Comparison and Analysis of Unsupervised Contrastive Learning Approaches for Korean Sentence Representations)

• Young Hyun Yoo, Kyumin Lee, Minjin Jeon, Jii Cha, Kangsan Kim, Taeuk Kim

• The 34th Annual Conference on Human and Cognitive Language Technology (HCLT 2022)