SMU-NLP Lab

Sookmyung Women's University Natural Language Processing Lab

SMU-NLP is the Natural Language Processing Lab at Sookmyung Women’s University. We work outward from language understanding and generation into AI agents, evaluation, resource building, human-integrated AI, and turning research results into real applications.

Our goal is to find problems nobody has properly solved yet and push the frontier of NLP research forward. We build the core techniques behind understanding and generating language, design agents that plan and act on their own, and work out evaluation methods we can actually trust. We explore how people and AI can work side by side, and carry what we learn into real applications.

contact

연구실 참여, 협업 등 문의는 아래 이메일로 연락주시기 바랍니다.

hyns.moon@sookmyung.ac.kr

news

Sep 25, 2026 Three papers have been accepted for publication at NeurIPS 2026.
  • [Main track] ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
  • [Evaluation & Datasets Track] MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
  • [Evaluation & Datasets Track] AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
Sep 02, 2026 Three papers have been accepted for publication at EMNLP 2026.
  • [Main] SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges
  • [Findings] DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
  • [Findings] SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
Sep 01, 2026 We are excited to announce the launch of the Natural Language Processing Lab (SMU-NLP) at Sookmyung Women’s University! Focusing on NLP, we actively research diverse topics including AI Agents, Data & Model Evaluation, Benchmarking, Resource Construction, and Multilinguality.

selected publications

  1. NeurIPS
    ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
    Joongmin Shin, Gyuho Shim, Hyeonseok Moon, and Jaehyung Seo
    The Fortieth Annual Conference on Neural Information Processing Systems, Dec 2026
  2. NeurIPS
    MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
    Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim
    The Fortieth Annual Conference on Neural Information Processing Systems Evaluations and Datasets Track, Dec 2026
  3. NeurIPS
    AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
    Chanhee Park, Jeongho Yoon, Sungbin Han, Hyeonseok Moon, and Heuiseok Lim
    The Fortieth Annual Conference on Neural Information Processing Systems Evaluations and Datasets Track, Dec 2026
  4. EMNLP
    SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges
    Seongtae Hong, Youngjoon Jang, Jia-Heui Ju, Hyeonseok Moon, and Heuiseok Lim
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, Oct 2026
  5. EMNLP
    SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
    Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim
    Findings of the Association for Computational Linguistics: EMNLP 2026, Oct 2026
  6. EMNLP
    DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
    Jungseob Lee, Seongtae Hong, Seungjun Lee, Jaehyung Seo, Junyoung Son, Sugyeong Eo, Chanjun Park, Hyeongju Park, Hyeonseok Moon, and Heuiseok Lim
    Findings of the Association for Computational Linguistics: EMNLP 2026, Oct 2026
  7. KBS
    SERA: Self-referential assessment framework for bidirectional generative commonsense reasoning
    Jaehyung Seo, Hyeonseok Moon, Yoonna Jang, and Heuiseok Lim
    Knowledge-Based Systems, 2026
    DOI
  8. ACL
    Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
    Jeongho Yoon, Chanhee Park, Yongchan Chun, Hyeonseok Moon, and Heuiseok Lim
    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026
    DOI
  9. ACL Findings
    NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
    Hyeonseok Moon and Heuiseok Lim
    Findings of the Association for Computational Linguistics: ACL 2026, Jul 2026
    DOI
  10. SIGIR
    Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation
    Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim
    Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026
    DOI
  11. ICLR
    Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment
    Seongtae Hong, Youngjoon Jang, Jungseob Lee, Hyeonseok Moon, and Heuiseok Lim
    The Fourteenth International Conference on Learning Representations, 2026
    HTML
  12. EMNLP
    Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models
    Hyeonseok Moon, Seongtae Hong, Jaehyung Seo, and Heuiseok Lim
    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025
    DOI
  13. EMNLP Findings
    LimaCost: Data Valuation for Instruction Tuning of Large Language Models
    Hyeonseok Moon, Jaehyung Seo, Seonmin Koo, Jinsung Kim, Young-kyoung Ham, Jiwon Moon, and Heuiseok Lim
    Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025
    DOI
  14. EMNLP
    The Impact of Negated Text on Hallucination with Large Language Models
    Jaehyung Seo, Hyeonseok Moon, and Heuiseok Lim
    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025
    DOI
  15. ACL
    Call for Rigor in Reporting Quality of Instruction Tuning Data
    Hyeonseok Moon, Jaehyung Seo, and Heuiseok Lim
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, Jul 2025
    DOI
  16. NAACL Findings
    Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models
    Hyeonseok Moon, Jaehyung Seo, Seungyoon Lee, Chanjun Park, and Heuiseok Lim
    Findings of the Association for Computational Linguistics: NAACL 2025, Apr 2025
    HTML