Abstract
The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this problem, we propose LM-Cocktail which enables the fine-tuned model to stay resilient in general perspectives. Our method is conducted in the form of model merging, where the fine-tuned language model is merged with the pre-trained base model or the peer models from other domains through weighted average. Despite simplicity, LM-Cocktail is surprisingly effective: the resulted model is able to achieve a strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain.- Anthology ID:
- 2024.findings-acl.145
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2474–2488
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.145
- DOI:
- Cite (ACL):
- Shitao Xiao, Zheng Liu, Peitian Zhang, and Xingrun Xing. 2024. LM-Cocktail: Resilient Tuning of Language Models via Model Merging. In Findings of the Association for Computational Linguistics ACL 2024, pages 2474–2488, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- LM-Cocktail: Resilient Tuning of Language Models via Model Merging (Xiao et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.145.pdf