THaLLE-ThaiLLM: Domain-Specialized Small LLMs for Finance and Thai -- Technical Report

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Labs, KBTG, :, Lertpiya, Anuruth, Khamnuansin, Danupat, Sucharitpongpan, Kantapong, Balee, Pornchanan, Chalothorn, Tawunrat, Pongthawornkamol, Thadpong, Lertsutthiwong, Monchai
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908753160306688
author Labs, KBTG
:
Lertpiya, Anuruth
Khamnuansin, Danupat
Sucharitpongpan, Kantapong
Balee, Pornchanan
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
author_facet Labs, KBTG
:
Lertpiya, Anuruth
Khamnuansin, Danupat
Sucharitpongpan, Kantapong
Balee, Pornchanan
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
contents Large Language Models (LLMs) have demonstrated significant potential across various domains, particularly in banking and finance, where they can automate complex tasks and enhance decision-making at scale. Due to privacy, security, and regulatory concerns, organizations often prefer on-premise deployment of LLMs. The ThaiLLM initiative aims to enhance Thai language capabilities in open-LLMs, enabling Thai industry to leverage advanced language models. However, organizations often face a trade-off between deploying multiple specialized models versus the prohibitive expense of training a single multi-capability model. To address this, we explore model merging as a resource-efficient alternative for developing high-performance, multi-capability LLMs. We present results from two key experiments: first, merging Qwen-8B with ThaiLLM-8B demonstrates how ThaiLLM-8B enhances Thai general capabilities, showing an uplift of M3 and M6 O-NET exams over the general instruction-following Qwen-8B. Second, we merge Qwen-8B with both ThaiLLM-8B and THaLLE-CFA-8B. This combination results in further improvements in performance across both general and financial domains, by demonstrating an uplift in both M3 and M6 O-NET, Flare-CFA, and Thai-IC benchmarks. The report showcases the viability of model merging for efficiently creating multi-capability LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04597
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle THaLLE-ThaiLLM: Domain-Specialized Small LLMs for Finance and Thai -- Technical Report
Labs, KBTG
:
Lertpiya, Anuruth
Khamnuansin, Danupat
Sucharitpongpan, Kantapong
Balee, Pornchanan
Chalothorn, Tawunrat
Pongthawornkamol, Thadpong
Lertsutthiwong, Monchai
Computation and Language
Large Language Models (LLMs) have demonstrated significant potential across various domains, particularly in banking and finance, where they can automate complex tasks and enhance decision-making at scale. Due to privacy, security, and regulatory concerns, organizations often prefer on-premise deployment of LLMs. The ThaiLLM initiative aims to enhance Thai language capabilities in open-LLMs, enabling Thai industry to leverage advanced language models. However, organizations often face a trade-off between deploying multiple specialized models versus the prohibitive expense of training a single multi-capability model. To address this, we explore model merging as a resource-efficient alternative for developing high-performance, multi-capability LLMs. We present results from two key experiments: first, merging Qwen-8B with ThaiLLM-8B demonstrates how ThaiLLM-8B enhances Thai general capabilities, showing an uplift of M3 and M6 O-NET exams over the general instruction-following Qwen-8B. Second, we merge Qwen-8B with both ThaiLLM-8B and THaLLE-CFA-8B. This combination results in further improvements in performance across both general and financial domains, by demonstrating an uplift in both M3 and M6 O-NET, Flare-CFA, and Thai-IC benchmarks. The report showcases the viability of model merging for efficiently creating multi-capability LLMs.
title THaLLE-ThaiLLM: Domain-Specialized Small LLMs for Finance and Thai -- Technical Report
topic Computation and Language
url https://arxiv.org/abs/2601.04597