Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914943025020928 |
|---|---|
| author | Yang, Yuncheng Qin, Yulei Wu, Tong Xu, Zihan Li, Gang Guo, Pengcheng Shao, Hang Shi, Yuchen Li, Ke Sun, Xing Yang, Jie Gu, Yun |
| author_facet | Yang, Yuncheng Qin, Yulei Wu, Tong Xu, Zihan Li, Gang Guo, Pengcheng Shao, Hang Shi, Yuchen Li, Ke Sun, Xing Yang, Jie Gu, Yun |
| contents | The cultivation of expertise for large language models (LLMs) to solve tasks of specific areas often requires special-purpose tuning with calibrated behaviors on the expected stable outputs. To avoid huge cost brought by manual preparation of instruction datasets and training resources up to hundreds of hours, the exploitation of open knowledge including a wealth of low rank adaptation (LoRA) models and instruction datasets serves as a good starting point. However, existing methods on model and data selection focus on the performance of general-purpose capabilities while neglecting the knowledge gap exposed in domain-specific deployment. In the present study, we propose to bridge such gap by introducing few human-annotated samples (i.e., K-shot) for advancing task expertise of LLMs with open knowledge. Specifically, we develop an efficient and scalable pipeline to cost-efficiently produce task experts where K-shot data intervene in selecting the most promising expert candidates and the task-relevant instructions. A mixture-of-expert (MoE) system is built to make the best use of individual-yet-complementary knowledge between multiple experts. We unveil the two keys to the success of a MoE system, 1) the abidance by K-shot, and 2) the insistence on diversity. For the former, we ensure that models that truly possess problem-solving abilities on K-shot are selected rather than those blind guessers. Besides, during data selection, instructions that share task-relevant contexts with K-shot are prioritized. For the latter, we highlight the diversity of constituting experts and that of the fine-tuning instructions throughout the model and data selection process. Extensive experimental results confirm the superiority of our approach over existing methods on utilization of open knowledge across various tasks. Our codes will be available at https://github.com/Yaphabates/Rocket. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15915 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models Yang, Yuncheng Qin, Yulei Wu, Tong Xu, Zihan Li, Gang Guo, Pengcheng Shao, Hang Shi, Yuchen Li, Ke Sun, Xing Yang, Jie Gu, Yun Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language The cultivation of expertise for large language models (LLMs) to solve tasks of specific areas often requires special-purpose tuning with calibrated behaviors on the expected stable outputs. To avoid huge cost brought by manual preparation of instruction datasets and training resources up to hundreds of hours, the exploitation of open knowledge including a wealth of low rank adaptation (LoRA) models and instruction datasets serves as a good starting point. However, existing methods on model and data selection focus on the performance of general-purpose capabilities while neglecting the knowledge gap exposed in domain-specific deployment. In the present study, we propose to bridge such gap by introducing few human-annotated samples (i.e., K-shot) for advancing task expertise of LLMs with open knowledge. Specifically, we develop an efficient and scalable pipeline to cost-efficiently produce task experts where K-shot data intervene in selecting the most promising expert candidates and the task-relevant instructions. A mixture-of-expert (MoE) system is built to make the best use of individual-yet-complementary knowledge between multiple experts. We unveil the two keys to the success of a MoE system, 1) the abidance by K-shot, and 2) the insistence on diversity. For the former, we ensure that models that truly possess problem-solving abilities on K-shot are selected rather than those blind guessers. Besides, during data selection, instructions that share task-relevant contexts with K-shot are prioritized. For the latter, we highlight the diversity of constituting experts and that of the fine-tuning instructions throughout the model and data selection process. Extensive experimental results confirm the superiority of our approach over existing methods on utilization of open knowledge across various tasks. Our codes will be available at https://github.com/Yaphabates/Rocket. |
| title | Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2408.15915 |