On the Potential of Tool-Enhanced Small
Language Models to Match Large Models in Finance

This repository contains the code and additional resources associated with the paper On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance, accepted for publication at The 6th ACM International Conference on AI in Finance (ICAIF ’25).

---

CITING

Gabriel Assis, Ayrton Surica, Pedro Kroll, Carina Munhoz, Darian Rabbani, Edson Bollis, Lucas Pellicer, and Aline Paes. 2025. On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance. In Proceedings of the 6th ACM International Conference on AI in Finance (ICAIF '25). Association for Computing Machinery, New York, NY, USA, 847–855. https://doi.org/10.1145/3768292.3770409

BIBTEX

@inproceedings{tool-small-llms-icaif25,
    author = {Assis, Gabriel and Surica, Ayrton and Kroll, Pedro and Munhoz, Carina and Rabbani, Darian and Bollis, Edson and Pellicer, Lucas and Paes, Aline},
    title = {On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance},
    year = {2025},
    isbn = {9798400722202},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3768292.3770409},
    doi = {10.1145/3768292.3770409},
    booktitle = {Proceedings of the 6th ACM International Conference on AI in Finance},
    pages = {847–855},
    numpages = {9},
    keywords = {Language Models, Tool-Enhanced Methods, Financial Question Answering},
    location = {Singapore, Singapore},
    series = {ICAIF '25}
}

FUNDING

This research was supported by the Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq, process 307088/2023-5); the Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro (FAPERJ, processes SEI-260003/002930/2024 and SEI-260003/000614/2023); and the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES, Finance Code 001). The authors would like to thank the Instituto de Ciência e Tecnologia Itaú (ICTi). All the conclusions expressed by the authors do not reflect the opinions of Itaú Unibanco and Instituto de Ciência e Tecnologia Itaú. Also, it must not result in any commercial process. Finally, all data used in this study comply with the Brazilian General Data Protection Law (LGPD).