Papers by Chun-Ying Huang
CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research (2024.emnlp-main)
Copied to clipboard
| Challenge: | Currently, command-line embeddings are limited due to the lack of comprehensive datasets for the field due to privacy and regulation concerns. |
| Approach: | They propose a command-line embedding model called CmdCaliper for training and unbiased evaluation using a set of large language models comprising 28,520 similar command- line pairs. |
| Outcome: | The proposed model suppresses state-of-the-art sentences with ten times more parameters across various tasks. |
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge (2025.findings-emnlp)
Copied to clipboard
Yan-Lun Chen, Yi-Ru Wei, Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang, Ying-Dar Lin, Yu-Sung Wu, Wei-Bin Lee
| Challenge: | Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine- tuned models often leads to degraded performance due to overlapping instruction-following components. |
| Approach: | They propose a layer-wise approach that assigns layer-specific weights to task vectors based on their alignment with instruction-following or task-specific components. |
| Outcome: | The proposed approach outperforms existing methods in learning and forgetting tasks while preserving overall model utility. |