Intent Classification for Bank Chatbots through LLM Fine-Tuning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lajčinová, Bibiána, Valábek, Patrik, Spišiak, Michal
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909338527858688
author Lajčinová, Bibiána
Valábek, Patrik
Spišiak, Michal
author_facet Lajčinová, Bibiána
Valábek, Patrik
Spišiak, Michal
contents This study evaluates the application of large language models (LLMs) for intent classification within a chatbot with predetermined responses designed for banking industry websites. Specifically, the research examines the effectiveness of fine-tuning SlovakBERT compared to employing multilingual generative models, such as Llama 8b instruct and Gemma 7b instruct, in both their pre-trained and fine-tuned versions. The findings indicate that SlovakBERT outperforms the other models in terms of in-scope accuracy and out-of-scope false positive rate, establishing it as the benchmark for this application.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04925
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Intent Classification for Bank Chatbots through LLM Fine-Tuning
Lajčinová, Bibiána
Valábek, Patrik
Spišiak, Michal
Computation and Language
I.2.7
This study evaluates the application of large language models (LLMs) for intent classification within a chatbot with predetermined responses designed for banking industry websites. Specifically, the research examines the effectiveness of fine-tuning SlovakBERT compared to employing multilingual generative models, such as Llama 8b instruct and Gemma 7b instruct, in both their pre-trained and fine-tuned versions. The findings indicate that SlovakBERT outperforms the other models in terms of in-scope accuracy and out-of-scope false positive rate, establishing it as the benchmark for this application.
title Intent Classification for Bank Chatbots through LLM Fine-Tuning
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2410.04925