是否集成：评估基于大型语言模型钓鱼检测的多数投票策略
To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models
AI总结：
本研究评估了三种多数投票策略（基于提示词、基于模型和混合集成）在LLM钓鱼URL检测中的表现，发现集成策略仅在个体组件性能相当时最有效，性能差异显著时不如最佳单一模型。
摘要：
大型语言模型（LLMs）的有效性在很大程度上依赖于其接收的提示词质量。然而，即使处理相同的提示词，由于训练过程的差异，LLMs也可能产生不同的结果。为了利用多个LLMs的集体智慧并提升其性能，本研究探讨了三种用于文本分类的多数投票策略，重点关注钓鱼URL检测。这些策略包括：（1）基于提示词的集成，利用单个LLM对各种提示词生成的响应进行多数投票；（2）基于模型的集成，将多个LLMs对单个提示词的响应进行聚合；（3）混合集成，结合上述两种方法，向多个LLMs发送不同提示词并聚合其响应。我们的分析表明，当各个组件表现出相当的性能水平时，集成策略最为适用。然而，当个体性能存在显著差异时，集成方法的有效性可能无法超过表现最佳的单个LLM或提示词。在这种情况下，不建议采用集成技术。
英文摘要：
The effectiveness of Large Language Models (LLMs) significantly relies on the quality of the prompts they receive. However, even when processing identical prompts, LLMs can yield varying outcomes due to differences in their training processes. To leverage the collective intelligence of multiple LLMs and enhance their performance, this study investigates three majority voting strategies for text classification, focusing on phishing URL detection. The strategies are: (1) a prompt-based ensemble, which utilizes majority voting across the responses generated by a single LLM to various prompts; (2) a model-based ensemble, which entails aggregating responses from multiple LLMs to a single prompt; and (3) a hybrid ensemble, which combines the two methods by sending different prompts to multiple LLMs and then aggregating their responses. Our analysis shows that ensemble strategies are most suited in cases where individual components exhibit equivalent performance levels. However, when there is a significant discrepancy in individual performance, the effectiveness of the ensemble method may not exceed that of the highest-performing single LLM or prompt. In such instances, opting for ensemble techniques is not recommended.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
