Pre-trained Large Language Models for Financial Sentiment Analysis

TL;DR

This paper demonstrates that adapting pre-trained large language models, specifically Llama2-7B, with supervised fine-tuning significantly improves financial sentiment analysis accuracy on news titles, even with limited training data.

Contribution

The study shows effective adaptation of Llama2-7B for financial sentiment classification, outperforming previous methods with minimal training samples.

Findings

Llama2-7B outperforms previous state-of-the-art algorithms.

Supervised fine-tuning enhances model performance in domain-specific tasks.

Small LLMs can achieve high accuracy in financial sentiment analysis.

Abstract

Financial sentiment analysis refers to classifying financial text contents into sentiment categories (e.g. positive, negative, and neutral). In this paper, we focus on the classification of financial news title, which is a challenging task due to a lack of large amount of training samples. To overcome this difficulty, we propose to adapt the pretrained large language models (LLMs) [1, 2, 3] to solve this problem. The LLMs, which are trained from huge amount of text corpora,have an advantage in text understanding and can be effectively adapted to domain-specific task while requiring very few amount of training samples. In particular, we adapt the open-source Llama2-7B model (2023) with the supervised fine-tuning (SFT) technique [4]. Experimental evaluation shows that even with the 7B model (which is relatively small for LLMs), our approach significantly outperforms the previous state-of-the-art algorithms.