Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.17421 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909591831314432 |
|---|---|
| author | Liu, Yang Yan, Bingjie Zou, Tianyuan Zhang, Jianqing Gu, Zixuan Ding, Jianbing Wang, Xidong Li, Jingyi Ye, Xiaozhou Ouyang, Ye Yang, Qiang Zhang, Ya-Qin |
| author_facet | Liu, Yang Yan, Bingjie Zou, Tianyuan Zhang, Jianqing Gu, Zixuan Ding, Jianbing Wang, Xidong Li, Jingyi Ye, Xiaozhou Ouyang, Ye Yang, Qiang Zhang, Ya-Qin |
| contents | Large language models (LLMs) have demonstrated remarkable capabilities, but they require vast amounts of data and computational resources. In contrast, smaller models (SMs), while less powerful, can be more efficient and tailored to specific domains. In this position paper, we argue that taking a collaborative approach, where large and small models work synergistically, can accelerate the adaptation of LLMs to private domains and unlock new potential in AI. We explore various strategies for model collaboration and identify potential challenges and opportunities. Building upon this, we advocate for industry-driven research that prioritizes multi-objective benchmarks on real-world private datasets and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks Liu, Yang Yan, Bingjie Zou, Tianyuan Zhang, Jianqing Gu, Zixuan Ding, Jianbing Wang, Xidong Li, Jingyi Ye, Xiaozhou Ouyang, Ye Yang, Qiang Zhang, Ya-Qin Machine Learning Artificial Intelligence Large language models (LLMs) have demonstrated remarkable capabilities, but they require vast amounts of data and computational resources. In contrast, smaller models (SMs), while less powerful, can be more efficient and tailored to specific domains. In this position paper, we argue that taking a collaborative approach, where large and small models work synergistically, can accelerate the adaptation of LLMs to private domains and unlock new potential in AI. We explore various strategies for model collaboration and identify potential challenges and opportunities. Building upon this, we advocate for industry-driven research that prioritizes multi-objective benchmarks on real-world private datasets and applications. |
| title | Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17421 |