LLM-Based Routing in Mixture of Experts: A Novel Framework for Trading

TL;DR

This paper introduces LLMoE, a novel framework that uses large language models as routers in a mixture-of-experts architecture to improve stock trading performance by leveraging multimodal data and contextual reasoning.

Contribution

The paper presents LLMoE, replacing traditional neural routers with LLMs to enhance expert selection in stock trading models, incorporating multimodal data and reasoning capabilities.

Findings

LLMoE outperforms existing MoE and neural network models on stock datasets.

The framework demonstrates improved interpretability and adaptability to various tasks.

Experimental results confirm the effectiveness of LLM-based routing in trading scenarios.

Abstract

Recent advances in deep learning and large language models (LLMs) have facilitated the deployment of the mixture-of-experts (MoE) mechanism in the stock investment domain. While these models have demonstrated promising trading performance, they are often unimodal, neglecting the wealth of information available in other modalities, such as textual data. Moreover, the traditional neural network-based router selection mechanism fails to consider contextual and real-world nuances, resulting in suboptimal expert selection. To address these limitations, we propose LLMoE, a novel framework that employs LLMs as the router within the MoE architecture. Specifically, we replace the conventional neural network-based router with LLMs, leveraging their extensive world knowledge and reasoning capabilities to select experts based on historical price data and stock news. This approach provides a more effective and interpretable selection mechanism. Our experiments on multimodal real-world stock datasets demonstrate that LLMoE outperforms state-of-the-art MoE models and other deep neural network approaches. Additionally, the flexible architecture of LLMoE allows for easy adaptation to various downstream tasks.