CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications
This work addresses financial analysis problems for NLP researchers, but it is incremental as it applies existing fine-tuning methods to a specific challenge.
The paper tackled financial tasks like classification, summarization, and trading by fine-tuning Llama3-8B and Mistral-7B models using PEFT and LoRA, and improved performance through data fusion from multiple tasks.
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.