mlsanityData to 7 Oct 2026

Enhancing Japanese Large Language Models with Reasoning Vectors

arXiv 2508.02913 ↗First posted 4 Aug 2025cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 10 of its 19 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

10 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Qwen3 Technical Report14 May
  2. 2024DeepSeek-V3 Technical Report27 Dec

Other references · 8

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2025s1: Simple test-time scalingcited by 1,311
  5. 2024Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilitiescited by 111
  6. 2025Unlocking Efficient Long-to-Short LLM Reasoning with Model Mergingcited by 58
  7. 2024LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMscited by 31
  8. 2025AnswerCarefully: A Dataset for Improving the Safety of Japanese LLM Outputcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Cost of Reasoning in non-English Languages: A Case Study on Japanese
  2. 2024Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs
  3. 2025Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
  4. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMs
  5. 2025Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
  6. 2026Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
  7. 2023Large Language Model Programs
  8. 2025Improving Reasoning Performance in Large Language Models via Representation Engineering