Unknown NLP Lab

저희는 9명의 자연어 처리 연구자 및 현직자로 이루어진 NLP 논문 리뷰 모임입니다. 지난 2023년 시작하여 2025년 여름 150 여개의 논문들을 리뷰하였습니다. 구성원들에 대한 자료는 people 란을 참고해주시기 바라며, 기타 문의는 jaehee_kim(at)snu.ac.kr로 연락 주시면 감사하겠습니다.

We are a group of nine natural language processing researchers and professionals. Since our inception in 2023, we have reviewed over 150 papers by the summer of 2025. For information about the members, please refer to the “People” section. For other inquiries, please contact jaehee_kim(at)snu.ac.kr.

news

Jan 15, 2016 A simple inline announcement with Markdown emoji! :sparkles: :smile:
Nov 07, 2015 A long announcement with details
Oct 22, 2015 A simple inline announcement.

latest posts

Aug 19, 2025 Spurious Rewards: Rethinking Training Signals in RLVR
Aug 19, 2025 ON THE GENERALIZATION OF SFT: A REINFORCEMENT LEARNING PERSPECTIVE WITH REWARD RECTIFICATION
Aug 12, 2025 What Makes a Reward Model a Good Teacher? An Optimization Perspective / The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models

selected publications

  1. EMNLP
    CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists
    Yukyung Lee, JoongHoon Kim, Jaehee Kim, and 4 more authors
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
  2. EMNLP
    COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection
    Jaewon Cheon and Pilsung Kang
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
  3. ACL
    Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning
    Joonwon Jang, Jaehee Kim, Wonbin Kweon, and 2 more authors
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025