Ensemble Learning for Large Language Models in Text and Code Generation: A Survey
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_ | 1866908478968168448 |
|---|---|
| author | Ashiga, Mari Jie, Wei Wu, Fan Voskanyan, Vardan Dinmohammadi, Fateme Brookes, Paul Gong, Jingzhi Wang, Zheng |
| author_facet | Ashiga, Mari Jie, Wei Wu, Fan Voskanyan, Vardan Dinmohammadi, Fateme Brookes, Paul Gong, Jingzhi Wang, Zheng |
| contents | Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and exhibit biases, limiting their representation of diverse language patterns. The closed-source nature of many powerful LLMs further restricts industry applications due to data privacy concerns. Inspired by successes in text generation, LLM ensemble techniques are now increasingly explored for code generation. This article reviews these emerging ensemble approaches to enhance understanding, encourage further research, and promote practical implementation in both text and code generation. We categorize LLM ensembles into seven main methods - weight merging, knowledge fusion, mixture-of-experts, reward ensemble, output ensemble, routing, and cascading - analyzing capabilities of those approaches. Our findings highlight key benefits such as improved diversity representation, enhanced output quality, and greater application flexibility. These insights aid model selection for real-world tasks and crucially, lay groundwork for extending ensemble strategies to multimodal LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13505 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ensemble Learning for Large Language Models in Text and Code Generation: A Survey Ashiga, Mari Jie, Wei Wu, Fan Voskanyan, Vardan Dinmohammadi, Fateme Brookes, Paul Gong, Jingzhi Wang, Zheng Computation and Language Artificial Intelligence Machine Learning Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and exhibit biases, limiting their representation of diverse language patterns. The closed-source nature of many powerful LLMs further restricts industry applications due to data privacy concerns. Inspired by successes in text generation, LLM ensemble techniques are now increasingly explored for code generation. This article reviews these emerging ensemble approaches to enhance understanding, encourage further research, and promote practical implementation in both text and code generation. We categorize LLM ensembles into seven main methods - weight merging, knowledge fusion, mixture-of-experts, reward ensemble, output ensemble, routing, and cascading - analyzing capabilities of those approaches. Our findings highlight key benefits such as improved diversity representation, enhanced output quality, and greater application flexibility. These insights aid model selection for real-world tasks and crucially, lay groundwork for extending ensemble strategies to multimodal LLMs. |
| title | Ensemble Learning for Large Language Models in Text and Code Generation: A Survey |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2503.13505 |