Ashiga, Mari, JIE, WEI ORCID: https://orcid.org/0000-0002-5392-0009, Wu, Fan, Voskanyan, Vardan, Dinmohammadi, Fateme, Brookes, Paul, Gong, Jingzhi, Wang, Zheng, Giavrimis, Rafail, Basios, Mike and Kanthan, Leslie (2026) Ensemble Learning for Large Language Models in text and code generation: a survey. IEEE Transactions on Artificial Intelligence. (In Press)

PDF Ensemble Learning for Large Language Models_JieW_AM_PdfA.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Attribution. Download (7MB) | Request a copy

Abstract

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 and agentic workflows.

Item Type:	Article
Subjects:	Computing
Date Deposited:	03 Mar 2026
URI:	https://repository.uwl.ac.uk/id/eprint/14687

Actions (admin access)