Papers by Hyun-Je Song
Selective Span-Level Unlearning for Large Language Models (2026.acl-short)
Copied to clipboard
| Challenge: | Existing selective methods that focus on identifying token-level or span-level unlearning targets are misaligning unlearning objectives with the model’s internal behavior. |
| Approach: | They propose a selective method that uses model-intrinsic information to identify token-level or span-level unlearning targets within a text rather than entire sequences. |
| Outcome: | The proposed method achieves comparable unlearning performance while significantly better preserving retained knowledge. |
Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model (D19-1)
Copied to clipboard
| Challenge: | Korean morphological analysis is a sequence of morpheme processing and POS tagging. |
| Approach: | They propose a tied sequence-to-sequence multi-task model for training the two tasks simultaneously without any explicit regularization. |
| Outcome: | The proposed model achieves state-of-the-art performance without any explicit regularization. |