Enhancing Financial Domain Adaptation of Language Models via Model Augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tanabe, Kota, Hirano, Masanori, Matoya, Kazuki, Imajo, Kentaro, Sakaji, Hiroki, Noda, Itsuki
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929681446469632
author Tanabe, Kota
Hirano, Masanori
Matoya, Kazuki
Imajo, Kentaro
Sakaji, Hiroki
Noda, Itsuki
author_facet Tanabe, Kota
Hirano, Masanori
Matoya, Kazuki
Imajo, Kentaro
Sakaji, Hiroki
Noda, Itsuki
contents The domain adaptation of language models, including large language models (LLMs), has become increasingly important as the use of such models continues to expand. This study demonstrates the effectiveness of Composition to Augment Language Models (CALM) in adapting to the financial domain. CALM is a model to extend the capabilities of existing models by introducing cross-attention between two LLMs with different functions. In our experiments, we developed a CALM to enhance the financial performance of an LLM with strong response capabilities by leveraging a financial-specialized LLM. Notably, the CALM was trained using a financial dataset different from the one used to train the financial-specialized LLM, confirming CALM's ability to adapt to various datasets. The models were evaluated through quantitative Japanese financial benchmarks and qualitative response comparisons, demonstrating that CALM enables superior responses with higher scores than the original models and baselines. Additionally, comparative experiments on connection points revealed that connecting the middle layers of the models is most effective in facilitating adaptation to the financial domain. These findings confirm that CALM is a practical approach for adapting LLMs to the financial domain.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09249
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Financial Domain Adaptation of Language Models via Model Augmentation
Tanabe, Kota
Hirano, Masanori
Matoya, Kazuki
Imajo, Kentaro
Sakaji, Hiroki
Noda, Itsuki
Computation and Language
Artificial Intelligence
The domain adaptation of language models, including large language models (LLMs), has become increasingly important as the use of such models continues to expand. This study demonstrates the effectiveness of Composition to Augment Language Models (CALM) in adapting to the financial domain. CALM is a model to extend the capabilities of existing models by introducing cross-attention between two LLMs with different functions. In our experiments, we developed a CALM to enhance the financial performance of an LLM with strong response capabilities by leveraging a financial-specialized LLM. Notably, the CALM was trained using a financial dataset different from the one used to train the financial-specialized LLM, confirming CALM's ability to adapt to various datasets. The models were evaluated through quantitative Japanese financial benchmarks and qualitative response comparisons, demonstrating that CALM enables superior responses with higher scores than the original models and baselines. Additionally, comparative experiments on connection points revealed that connecting the middle layers of the models is most effective in facilitating adaptation to the financial domain. These findings confirm that CALM is a practical approach for adapting LLMs to the financial domain.
title Enhancing Financial Domain Adaptation of Language Models via Model Augmentation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.09249