Abstract
With the advance of large language models (LLMs), LLMs have been utilized for the various tasks. However, the issues of variability and reproducibility of results from each trial of LLMs have been largely overlooked in existing literature while actual human annotation uses majority voting to resolve disagreements among annotators. Therefore, this study introduces the straightforward ensemble strategy to a sentiment analysis using LLMs. As the results, we demonstrate that the ensemble of multiple inference using medium-sized LLMs produces more robust and accurate results than using a large model with a single attempt with reducing RMSE by 18.6%.
Abstract (translated)
随着大型语言模型（LLM）的发展，这些模型已被应用于各种任务。然而，在现有文献中，人们对于每次试验结果的可变性和再现性问题关注不足，而实际的人工标注过程中会使用多数投票来解决注释者之间的分歧。因此，本研究提出了一种简单有效的集成策略，用于基于LLM的情感分析。结果显示，通过使用多个中型LLM进行集合推理可以产生比单一大型模型尝试更稳健和准确的结果，从而将均方根误差（RMSE）降低了18.6%。
URL
https://arxiv.org/abs/2504.18884
