Exploration and selection of LLM models for financial text simplification

Article Sidebar

PDF
Published: 2024-09-09
DOI: https://doi.org/10.18845/tm.v37i7.7297
Keywords:
LLM models, simplification, SARI, BLEU, AI, Llama, financial data

Main Article Content

Bertha C Brenes-Brenes
Instituto Tecnológico de Costa Rica
https://orcid.org/0009-0008-1303-7263
Saul Calderón-Ramírez
Instituto Tecnológico de Costa Rica
https://orcid.org/0000-0001-9993-4388

Abstract

This research is dedicated to the simplification of Spanish-language financial texts to enhance
accessibility for screen readers. We present a qualitative and quantitative analysis of the text
simplification process, employing a set of Spanish simplification rules and metrics. Our study
evaluates the outcomes resulting from the application of three distinct financial datasets to
four pre-trained models. The primary objective is to identify the most effective models for
text simplification and determine those warranting further investment through fine-tuning and
training. This study contributes to improving the accessibility and comprehensibility of financial
documents for individuals with visual impairments.

Article Details

Issue

2024: Vol. 37, special issue. IEEE International Conference on BioInspired Processing

Section

Artículo científico
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación  y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos.  Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.

How to Cite

Exploration and selection of LLM models for financial text simplification. (2024). Tecnología en Marcha Journal, 37(7), Pág 50-56. https://doi.org/10.18845/tm.v37i7.7297

References

P. Menon. (2023). Introduction to Large Language Models and the Transformer Architecture

V.Chaudhary.(2023).Transformers and LLMs: The Next Frontier in AI, ur(https://www.linkedin.com/pulse/

transformers-llms-next-frontier-ai-vijay-chaudhary/)

Legible. Fórmula de Crawford, url(https://legible.es/blog/formula-de-crawford/ )

K.North,M.Zampieri, M.Shardlow.(2023). Lexical Complexity Prediction: An Overview, url(https://dl.acm.org/

doi/10.1145/3557885)

K. Doshi(2021). Foundations of NLP Explained — Bleu Score and WER Metrics, https://towardsdatascience.com/foundations-of-nlp-explained-bleu-score-and-wer-metrics-1a5ba06d812b Repo: https://github.com/

BerthaBrenes/Text-Simplification-with-LLM