Adapters Selector: Cross-domains and Multi-tasks LoRA Modules Integration Usage Method

Yimin Tian, Bolin Zhang, Zhiying Tu, Dianhui Chu


Abstract
Parameter-Efficient Fine-Tuning (PEFT) adapts large language models (LLMs) to specific domains by updating only a small portion of the parameters. Although fine-tuning on a single task within a specific domain has demonstrated promising results, there remains limited exploration on how to effectively integrate these adapters for optimal performance. In this paper, we propose Adapters Selector (AS): a novel framework for better integrating usage of multiple adapters by training a middleman adapter to select the appropriate adapter for inference. Our approach utilizes PEFT to train a selector that determines which input content corresponds to which task in which domain, and subsequently selects the homologous adapter. By the way, The AS has developed the capability to execute cross-domain multi-tasks effectively through the utilization of a compact model in combination with multiple LoRA modules. Our code is publicly available.
Anthology ID:
2025.coling-main.40
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
593–605
Language:
URL:
https://aclanthology.org/2025.coling-main.40/
DOI:
Bibkey:
Cite (ACL):
Yimin Tian, Bolin Zhang, Zhiying Tu, and Dianhui Chu. 2025. Adapters Selector: Cross-domains and Multi-tasks LoRA Modules Integration Usage Method. In Proceedings of the 31st International Conference on Computational Linguistics, pages 593–605, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Adapters Selector: Cross-domains and Multi-tasks LoRA Modules Integration Usage Method (Tian et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.40.pdf