| Autor: |
Lu, Keer, Zhao, Keshi, Liang, Zheng, Pan, Da, Zhang, Shusen, Wu, Xin, Chen, Weipeng, Zhou, Zenan, Dong, Guosheng, Cui, Bin, Zhang, Wentao |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
Large Language Models (LLMs) exhibit remarkable capabilities in handling multiple tasks across domains due to their emergent properties. These capabilities are further augmented during the Supervised Fine-Tuning (SFT) phase. Despite their potential, existing work mainly focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains. In this study, we introduce VersaTune, a novel data composition framework designed for enhancing LLMs' overall multi-ability performances during fine-tuning. We categorize knowledge into distinct domains including law, medicine, finance, science, code. We begin with detecting the distribution of domain-specific knowledge within the base model, followed by the composition of training data that aligns with the model's existing knowledge distribution. During the fine-tuning process, weights of different domains are dynamically adjusted based on their learnable potential and forgetting degree. Experimental results demonstrate that VersaTune achieves significant improvements in multi-domain performance, with a 35.21% enhancement in comprehensive multi-domain tasks. Additionally, in scenarios where specific domain optimization is required, VersaTune reduces the degradation of performance in other domains by 38.77%, without compromising the target domain's training efficacy. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
