Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911195050541056 |
|---|---|
| author | Djagba, Prudence Saley, Abdelkader Y. |
| author_facet | Djagba, Prudence Saley, Abdelkader Y. |
| contents | This research explores the strengths and weaknesses of domain-adapted Large Language Models (LLMs) in the context of financial natural language processing (NLP). The analysis centers on FinMA, a model created within the PIXIU framework, which is evaluated for its performance in specialized financial tasks. Recognizing the critical demands of accuracy, reliability, and domain adaptation in financial applications, this study examines FinMA's model architecture, its instruction tuning process utilizing the Financial Instruction Tuning (FIT) dataset, and its evaluation under the FLARE benchmark. Findings indicate that FinMA performs well in sentiment analysis and classification, but faces notable challenges in tasks involving numerical reasoning, entity recognition, and summarization. This work aims to advance the understanding of how financial LLMs can be effectively designed and evaluated to assist in finance-related decision-making processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05151 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA Djagba, Prudence Saley, Abdelkader Y. Computation and Language Machine Learning This research explores the strengths and weaknesses of domain-adapted Large Language Models (LLMs) in the context of financial natural language processing (NLP). The analysis centers on FinMA, a model created within the PIXIU framework, which is evaluated for its performance in specialized financial tasks. Recognizing the critical demands of accuracy, reliability, and domain adaptation in financial applications, this study examines FinMA's model architecture, its instruction tuning process utilizing the Financial Instruction Tuning (FIT) dataset, and its evaluation under the FLARE benchmark. Findings indicate that FinMA performs well in sentiment analysis and classification, but faces notable challenges in tasks involving numerical reasoning, entity recognition, and summarization. This work aims to advance the understanding of how financial LLMs can be effectively designed and evaluated to assist in finance-related decision-making processes. |
| title | Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2510.05151 |