Abstract
Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or tool-use decisions. A central deployment question is whether these skills should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging. We study this question using thirteen models spanning five families (Qwen3, Qwen3.5, Gemma-3, Llama-3.1, and Mistral) from 0.6B to 32B parameters across eight customer-support datasets, spanning four public and four proprietary datasets with approximately 74.5k training and 8.7k evaluation samples. Under a fixed training protocol, we train more than 200 checkpoints. Our experiments reveal that multi-task full fine-tuning is the strongest operational default at every model size we test. Specialist models are strong on their target tasks but often degrade sharply off-task, making reliable routing important. Sequential Low-Rank Adaptation (LoRA) preserves earlier skills better than sequential full fine-tuning, while merging a specialist with its base model improves off-task robustness with limited same-task loss for larger models. We conclude with practical guidelines for selecting fine-tuning strategies in real-world settings.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Laskar, M. T. R., Fu, X. Y., & TN, S. B. (2026). Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs. https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms
MLA 9
Laskar, Md Tahmid Rahman, et al. "Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs." https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms.
Chicago (author–date)
Laskar, Md Tahmid Rahman, Xue-Yong Fu, and Shashi Bhushan TN. 2026. "Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs." https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms.
Harvard
Laskar, M. T. R., Fu, X. Y. and TN, S. B. (2026) 'Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs', Available at: https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms.
Vancouver
Laskar MTR, Fu XY, TN SB. Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs. https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms
IEEE
M. T. R. Laskar, X. Y. Fu, and S. B. TN, "Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs," https://omanscience.com/en/articles/can-one-adapted-model-do-it-all-fine-tuning-strategy-selection-for-customer-support-llms.