CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915019302633472 |
|---|---|
| author | Mohajeri, Mohammad Mahdi Dousti, Mohammad Javad Ahmadabadi, Majid Nili |
| author_facet | Mohajeri, Mohammad Mahdi Dousti, Mohammad Javad Ahmadabadi, Majid Nili |
| contents | Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across various domains. However, the performance of LLMs heavily depends on the quality of their input prompts. Recent studies have also shown that LLMs exhibit remarkable results in code-related tasks. To leverage the capabilities of LLMs in text classification, we propose the Code Completion Prompt (CoCoP) method, which transforms the text classification problem into a code completion task. CoCoP significantly improves text classification performance across diverse datasets by utilizing LLMs' code-completion capability. For instance, CoCoP enhances the accuracy of the SST2 dataset by more than 20%. Moreover, when CoCoP integrated with LLMs specifically designed for code-related tasks (code models), such as CodeLLaMA, this method demonstrates better or comparable performance to few-shot learning techniques while using only one-tenth of the model size. The source code of our proposed method will be available to the public upon the acceptance of the paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08979 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt Mohajeri, Mohammad Mahdi Dousti, Mohammad Javad Ahmadabadi, Majid Nili Computation and Language Artificial Intelligence Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across various domains. However, the performance of LLMs heavily depends on the quality of their input prompts. Recent studies have also shown that LLMs exhibit remarkable results in code-related tasks. To leverage the capabilities of LLMs in text classification, we propose the Code Completion Prompt (CoCoP) method, which transforms the text classification problem into a code completion task. CoCoP significantly improves text classification performance across diverse datasets by utilizing LLMs' code-completion capability. For instance, CoCoP enhances the accuracy of the SST2 dataset by more than 20%. Moreover, when CoCoP integrated with LLMs specifically designed for code-related tasks (code models), such as CodeLLaMA, this method demonstrates better or comparable performance to few-shot learning techniques while using only one-tenth of the model size. The source code of our proposed method will be available to the public upon the acceptance of the paper. |
| title | CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.08979 |