Saved in:
Bibliographic Details
Main Authors: Oguchi, Carolina Minami, Wei, Leo, Kobayashi, Koyo, Wu, Hsin-Tai, Ghosal, Dipak
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02913
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912519748059136
author Oguchi, Carolina Minami
Wei, Leo
Kobayashi, Koyo
Wu, Hsin-Tai
Ghosal, Dipak
author_facet Oguchi, Carolina Minami
Wei, Leo
Kobayashi, Koyo
Wu, Hsin-Tai
Ghosal, Dipak
contents Post-training methods have improved the performance and enhanced the reasoning capability for mainstream large language models (LLMs), but the same is challenging for Japanese LLMs to achieve due to the amount of resources required. Inspired by task vectors that extract the change of weights before and after training, specifically for a certain task, we obtain reasoning vectors from reasoning LLMs and apply them to Japanese LLMs to boost their performance. While the resources available present a challenge to improve Japanese LLMs, we present a simple and effective way to obtain high improvement and hope to inspire for other languages.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02913
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Japanese Large Language Models with Reasoning Vectors
Oguchi, Carolina Minami
Wei, Leo
Kobayashi, Koyo
Wu, Hsin-Tai
Ghosal, Dipak
Artificial Intelligence
Post-training methods have improved the performance and enhanced the reasoning capability for mainstream large language models (LLMs), but the same is challenging for Japanese LLMs to achieve due to the amount of resources required. Inspired by task vectors that extract the change of weights before and after training, specifically for a certain task, we obtain reasoning vectors from reasoning LLMs and apply them to Japanese LLMs to boost their performance. While the resources available present a challenge to improve Japanese LLMs, we present a simple and effective way to obtain high improvement and hope to inspire for other languages.
title Enhancing Japanese Large Language Models with Reasoning Vectors
topic Artificial Intelligence
url https://arxiv.org/abs/2508.02913