Harnessing Multiple Large Language Models: A Survey on LLM Ensemble
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917426738757632 |
|---|---|
| author | Chen, Zhijun Lu, Xiaodong Li, Jingzheng Chen, Pengpeng Li, Zhuoran Sun, Kai Luo, Yuankai Mao, Qianren Li, Ming Xiao, Likang Yang, Dingqi Huang, Xiao Ban, Yikun Sun, Hailong Yu, Philip S. |
| author_facet | Chen, Zhijun Lu, Xiaodong Li, Jingzheng Chen, Pengpeng Li, Zhuoran Sun, Kai Luo, Yuankai Mao, Qianren Li, Ming Xiao, Likang Yang, Dingqi Huang, Xiao Ban, Yikun Sun, Hailong Yu, Philip S. |
| contents | LLM Ensemble -- which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths -- has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of "ensemble-before-inference, ensemble-during-inference, ensemble-after-inference'', and review all relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest several future research directions. A curated list of papers on LLM Ensemble is available at https://github.com/junchenzhi/Awesome-LLM-Ensemble. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18036 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Harnessing Multiple Large Language Models: A Survey on LLM Ensemble Chen, Zhijun Lu, Xiaodong Li, Jingzheng Chen, Pengpeng Li, Zhuoran Sun, Kai Luo, Yuankai Mao, Qianren Li, Ming Xiao, Likang Yang, Dingqi Huang, Xiao Ban, Yikun Sun, Hailong Yu, Philip S. Computation and Language LLM Ensemble -- which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths -- has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of "ensemble-before-inference, ensemble-during-inference, ensemble-after-inference'', and review all relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest several future research directions. A curated list of papers on LLM Ensemble is available at https://github.com/junchenzhi/Awesome-LLM-Ensemble. |
| title | Harnessing Multiple Large Language Models: A Survey on LLM Ensemble |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.18036 |