Large Language Models (LLMs) excel in general tasks but struggle with domain-specific challenges, such as specialized terminology and localized regulations. Existing financial LLMs, like FinGPT and BloombergGPT, lack support for the Thai financial domain. We developed a Thai Financial LLM using the Investment Consultant (IC) exam dataset from the Stock Exchange of Thailand. To address dataset limitations, we applied data augmentation, ReLoRA for efficient training, Continued Pretraining (CPT) for domain knowledge, and Rank-Stabilized LoRA (rsLoRA) for fine-tuning. Supervised Fine-Tuning (SFT) simulated exam scenarios, while Direct Preference Optimization (DPO) refined the model using feedback. The model achieved scores of 72%, 72%, and 84% on IC exam levels P1, P2, and P3, respectively, demonstrating its effectiveness in Thai financial advisory tasks and its potential for specialized applications.
@article{arxiv.2411.18242,
title = {Thai Financial Domain Adaptation of THaLLE -- Technical Report},
author = {KBTG Labs and Atthakorn Petchsod and Pornchanan Balee and Danupat Khamnuansin and Anuruth Lertpiya and Chanatip Saetia and Tawunrat Chalothorn and Thadpong Pongthawornkamol and Monchai Lertsutthiwong},
journal= {arXiv preprint arXiv:2411.18242},
year = {2024}
}