Comparing LLMs for Sentiment Analysis in Financial Market News

This article presents a comparative study of large language models (LLMs) in the task of sentiment analysis of fi nancial market news. This work aims to analyze the performance difference of these models in this important natural language processing task within the context of fi nance. LLM models are compared with classical approaches, allowing for the quanti fi cation of the bene fi ts of each tested model or approach. Results show that large language models outperform classical models in the vast majority of cases.