Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909057020854272 |
|---|---|
| author | Zhu, Shaojie Wang, Zhaobin Zhuo, Chengxiang Lu, Hui Hu, Bo Li, Zang |
| author_facet | Zhu, Shaojie Wang, Zhaobin Zhuo, Chengxiang Lu, Hui Hu, Bo Li, Zang |
| contents | CoT (Chain-of-Thought) is a way to solve reasoning problems for LLMs . Recently, many researches appear for improving the CoT capability of LLMs. In this work, we also proposed Olapa-MCoT, which is a LLMs based on llama2-13B PLM for finetuning and alignment learning. During the alignment training, we proposed the SimRRHF algorithm and Incorrect Data Relearning and mainly focused on optimizing the Chinese mathematical reasoning ability of Olapa-MCoT. The experiment achieved significant results, with the accuracy of Chinese mathematical reasoning up to 50%, 36% rise compared to llama2-13B. In addition, the accuracy of English reasoning ability also increased by nearly 4%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_17535 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs Zhu, Shaojie Wang, Zhaobin Zhuo, Chengxiang Lu, Hui Hu, Bo Li, Zang Artificial Intelligence Computation and Language Human-Computer Interaction CoT (Chain-of-Thought) is a way to solve reasoning problems for LLMs . Recently, many researches appear for improving the CoT capability of LLMs. In this work, we also proposed Olapa-MCoT, which is a LLMs based on llama2-13B PLM for finetuning and alignment learning. During the alignment training, we proposed the SimRRHF algorithm and Incorrect Data Relearning and mainly focused on optimizing the Chinese mathematical reasoning ability of Olapa-MCoT. The experiment achieved significant results, with the accuracy of Chinese mathematical reasoning up to 50%, 36% rise compared to llama2-13B. In addition, the accuracy of English reasoning ability also increased by nearly 4%. |
| title | Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs |
| topic | Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2312.17535 |