Youna Kim

About

I'm a Ph.D. candidate in the Graduate School of Artificial Intelligence, Seoul National University. I work on Natural Language Processing, with a particular interest in the reliable integration of external knowledge and model knowledge.

Feel free to reach out if you'd like to connect or explore potential collaborations! 😄

Education

• 2021 - Present: Ph.D. at Seoul National University, Graduate School of Artificial Intelligence
  Supervised by Prof. Sang-goo Lee
• 2017 - 2020: B.S. at University of Wisconsin-Madison
  Double Major in Computer Science & Statistics

Publications

• CUB: Benchmarking Context Utilisation Techniques for Language Models
  Lovisa Hagström^*, Youna Kim^*, Haeun Yu, Sang-goo Lee, Richard Johansson, Hyunsoo Cho, Isabelle Augenstein (^*Equal contribution)
  Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) [Paper] [Code]
• When to Speak, When to Abstain: Contrastive Decoding with Abstention
  Hyuhng Joon Kim, Youna Kim, Sang-goo Lee, Taeuk Kim
  Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) [Paper]
• Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
  Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
  Findings of the Association for Computational Linguistics: EMNLP 2024 [Paper] [Code]
• Aligning Language Models to Explicitly Handle Ambiguity
  Hyuhng Joon Kim, Youna Kim, Cheonbok Park, Junyeob Kim, Choonghyun Park, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
  Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) [Paper]
• CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
  Hyunsoo Cho, Youna Kim, Sang-goo Lee
  Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023) [Paper]
• Multi-Scale Contrastive Learning for Complex Scene Generation
  Hanbit Lee, Youna Kim, Sang-goo Lee
  Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023) [Paper]

Preprints (arXiv)

• UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge
  Youna Kim, Hyuhng Joon Kim, Minjoon Choi, Sungmin Cho, Hyunsoo Cho, Sang-goo Lee, Taeuk Kim
  Under Review [Paper]

Experience

• Sep. 2019 - Dec. 2020: IT Programmer, Goldsmith Lab, Waisman Center, Madison, WI
  Streamlined the Waisman Twin Project by developing automated applications to manage, share, and score psychological research data.