G-Boost: Boosting Private SLMs with General LLMs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916651841093632 |
|---|---|
| author | Fan, Yijiang Mao, Yuren Lai, Longbin Zhang, Ying Qian, Zhengping Gao, Yunjun |
| author_facet | Fan, Yijiang Mao, Yuren Lai, Longbin Zhang, Ying Qian, Zhengping Gao, Yunjun |
| contents | Due to the limited computational resources, most Large Language Models (LLMs) developers can only fine-tune Small Language Models (SLMs) on their own data. These private SLMs typically have limited effectiveness. To boost the performance of private SLMs, this paper proposes to ask general LLMs for help. The general LLMs can be APIs or larger LLMs whose inference cost the developers can afford. Specifically, we propose the G-Boost framework where a private SLM adaptively performs collaborative inference with a general LLM under the guide of process reward. Experiments demonstrate that our framework can significantly boost the performance of private SLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10367 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | G-Boost: Boosting Private SLMs with General LLMs Fan, Yijiang Mao, Yuren Lai, Longbin Zhang, Ying Qian, Zhengping Gao, Yunjun Computation and Language Artificial Intelligence Due to the limited computational resources, most Large Language Models (LLMs) developers can only fine-tune Small Language Models (SLMs) on their own data. These private SLMs typically have limited effectiveness. To boost the performance of private SLMs, this paper proposes to ask general LLMs for help. The general LLMs can be APIs or larger LLMs whose inference cost the developers can afford. Specifically, we propose the G-Boost framework where a private SLM adaptively performs collaborative inference with a general LLM under the guide of process reward. Experiments demonstrate that our framework can significantly boost the performance of private SLMs. |
| title | G-Boost: Boosting Private SLMs with General LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.10367 |