Papers by Youngsub Han
ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining (2025.emnlp-industry)
Copied to clipboard
Seonwu Kim, Yohan Na, Kihun Kim, Hanhee Cho, Geun Lim, Mintae Kim, Seongik Park, Ki Hyun Kim, Youngsub Han, Byoung-Ki Jeon
| Challenge: | Domain Adaptive Continual Pretraining (DACP) is a method to mitigate performance degradation in small LLMs and enhance their effectiveness in target domains. |
| Approach: | They propose a continual pretraining methodology that optimizes sLLMs within service domains and enhances their effectiveness in target domains. |
| Outcome: | The proposed model achieves significant gains in target-domain performance while preserving general capabilities, offering a cost-efficient and scalable solution for enterprise-level deployment. |
SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches for document-grounded dialogue systems are based on retrieve-and-generate frameworks. |
| Approach: | They propose a novel extension to improve document grounded response generation by incorporating a copy mechanism into a augmentation. |
| Outcome: | The proposed extension improves the document-grounded response generation performance even with the base reader. |