CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications

TL;DR

This paper demonstrates how fine-tuning large language models with data fusion techniques can improve performance across multiple financial NLP tasks, including classification, summarization, and trading prediction.

Contribution

It introduces a novel approach of combining datasets and applying PEFT and LoRA methods to enhance LLMs for financial applications.

Findings

Improved accuracy in financial classification and summarization.

Effective data fusion enhances model performance.

Demonstrated capacity of LLMs in complex financial tasks.

Abstract

The integration of Large Language Models (LLMs) into financial analysis has garnered significant attention in the NLP community. This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks: financial classification, financial text summarization, and single stock trading. We adopted Llama3-8B and Mistral-7B as base models, fine-tuning them through Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA) approaches. To enhance model performance, we combine datasets from task 1 and task 2 for data fusion. Our approach aims to tackle these diverse tasks in a comprehensive and integrated manner, showcasing LLMs' capacity to address diverse and complex financial tasks with improved accuracy and decision-making capabilities.