Financial News Analytics Using Fine-Tuned Llama 2 GPT Model
This addresses financial analysts' need for automated news processing, but it is incremental as it applies existing fine-tuning methods to a specific domain.
The paper fine-tuned the Llama 2 GPT model using PEFT/LoRA for multitask analysis of financial news, including perspective analysis, summarization, and sentiment extraction, enabling structured and JSON-formatted outputs for predictive features.
The paper considers the possibility to fine-tune Llama 2 GPT large language model (LLM) for the multitask analysis of financial news. For fine-tuning, the PEFT/LoRA based approach was used. In the study, the model was fine-tuned for the following tasks: analysing a text from financial market perspectives, highlighting main points of a text, summarizing a text and extracting named entities with appropriate sentiments. The obtained results show that the fine-tuned Llama 2 model can perform a multitask financial news analysis with a specified structure of response, part of response can be a structured text and another part of data can have JSON format for further processing. Extracted sentiments for named entities can be considered as predictive features in supervised machine learning models with quantitative target variables.