English

Intent Classification for Bank Chatbots through LLM Fine-Tuning

Computation and Language 2024-10-08 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2410.04925,
  title  = {Intent Classification for Bank Chatbots through LLM Fine-Tuning},
  author = {Bibiána Lajčinová and Patrik Valábek and Michal Spišiak},
  journal= {arXiv preprint arXiv:2410.04925},
  year   = {2024}
}

Comments

7 pages, no figures

R2 v1 2026-06-28T19:10:58.217Z