aiqbench analysis
This research introduces Olapa-MCoT, a method designed to significantly boost Chinese mathematical reasoning capabilities in large language models without degrading performance on other tasks. By leveraging techniques like Similarity RRHF and Incorrect Data Relearning, the study demonstrates that specialized fine-tuning can effectively address specific linguistic and logical gaps in foundational models. The approach offers a practical pathway for improving model utility in non-English contexts while maintaining general reasoning strengths.
Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
arXiv:2312.17535v2 Announce Type: replace Abstract: In the past two years, the outstanding performance of ChatGPT in multilingual and multitasking has led to large language models (LLMs) attracting widespread attention. However, restricted by expensive costs, many studies have to focus on the ability of only one major language. How can we quickly improve the model's capabilities in new languages without reducing its original capabilities under limited data and computing power? In this work, we focus on improving the Chinese mathematical reasoning capability based on Llama-2-13B, which is weak in Chinese mathematical reasoning. We proposed the Mathematical Chain of Thought method (Olapa-MCoT). First, we propose Similarity RRHF (SimRRHF), which adds the constraint of model optimization direction by introducing similarity loss based on RRHF. Furthermore, the novelty Incorrect Data Relearning (IDRL) method is designed, which improves the model's ability to learn difficult knowledge. The experiment achieves significant performance, with the accuracy of Chinese mathematical reasoning up to 50%, a 36% rise compared to Llama-2-13B-chat. In addition, the accuracy of English reasoning ability also increased by nearly 4%. It is worth mentioning that our method can be applied to any language major LLMs.
Abstract:In the past two years, the outstanding performance of ChatGPT in multilingual and multitasking has led to large language models (LLMs) attracting widespread attention. However, restricted by expensive costs, many studies have to focus on the ability of only one major language. How can we quickly improve the model's capabilities in new languages without reducing its original capabilities under limited data and computing power? In this work, we focus on improving the Chinese mathematical reasoning capability based on Llama-2-13B, which is weak in Chinese mathematical reasoning. We proposed the Mathematical Chain of Thought method (Olapa-MCoT). First, we propose Similarity RRHF (SimRRHF), which adds the constraint of model optimization direction by introducing similarity loss based on RRHF. Furthermore, the novelty Incorrect Data Relearning (IDRL) method is designed, which improves the model's ability to learn difficult knowledge. The experiment achieves significant performance, with the accuracy of Chinese mathematical reasoning up to 50%, a 36% rise compared to Llama-2-13B-chat. In addition, the accuracy of English reasoning ability also increased by nearly 4%. It is worth mentioning that our method can be applied to any language major LLMs.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
arXiv:2312.17535 [cs.AI]
(or arXiv:2312.17535v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2312.17535 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 283 words
Related coverage
Links #3: 2026/06 Part 1
LessWrong · Jun 15, 2026
ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model
arXiv · Aug 25, 2026
[AINews] not much happened today
Latent Space · Sep 18, 2026
Controllable-CoT leads to covert reasoning capabilities
LessWrong · Sep 22, 2026