SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation
Luo, Junyu, Luo, Xiao, Chen, Xiusi, Xiao, Zhiping, Ju, Wei, Zhang, Ming
–arXiv.org Artificial Intelligence
Supervised fine-tuning (SFT) is crucial in adapting large language models (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in yielding satisfactory results. Therefore, a data-efficient framework that can fully exploit labeled and unlabeled data for LLM fine-tuning is highly anticipated. Towards this end, we introduce a semi-supervised fine-tuning framework named SemiEvol for LLM adaptation from a propagate-and-select manner. For knowledge propagation, SemiEvol adopts a bi-level approach, propagating knowledge from labeled data to unlabeled data through both in-weight and in-context methods. For knowledge selection, SemiEvol incorporates a collaborative learning mechanism, selecting higher-quality pseudo-response samples. We conducted experiments using GPT-4o-mini and Llama-3.1 on seven general or domain-specific datasets, demonstrating significant improvements in model performance on target data. Furthermore, we compared SemiEvol with SFT and self-evolution methods, highlighting its practicality in hybrid data scenarios.
arXiv.org Artificial Intelligence
Oct-17-2024
- Country:
- North America > United States
- Illinois > Champaign County
- Urbana (0.04)
- California > Los Angeles County
- Los Angeles (0.14)
- Illinois > Champaign County
- Europe > Germany
- Berlin (0.04)
- Asia > Thailand
- North America > United States
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Health & Medicine (0.46)
- Technology: