Thai Financial Domain Adaptation of THaLLE -- Technical Report

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Labs, KBTG, Petchsod, Atthakorn, Balee, Pornchanan, Khamnuansin, Danupat, Lertpiya, Anuruth, Saetia, Chanatip, Chalothorn, Tawunrat, Pongthawornkamol, Thadpong, Lertsutthiwong, Monchai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915037182951424
author Labs, KBTG
Petchsod, Atthakorn
Balee, Pornchanan
Khamnuansin, Danupat
Lertpiya, Anuruth
Saetia, Chanatip
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
author_facet Labs, KBTG
Petchsod, Atthakorn
Balee, Pornchanan
Khamnuansin, Danupat
Lertpiya, Anuruth
Saetia, Chanatip
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thai Financial Domain Adaptation of THaLLE -- Technical Report
Labs, KBTG
Petchsod, Atthakorn
Balee, Pornchanan
Khamnuansin, Danupat
Lertpiya, Anuruth
Saetia, Chanatip
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
Computation and Language
Artificial Intelligence
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.
title Thai Financial Domain Adaptation of THaLLE -- Technical Report
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.18242