CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
This addresses the challenge of prompt dependency in LLMs for text classification, offering a novel approach that leverages code-completion capabilities, though it appears incremental as it builds on existing LLM and code model techniques.
The paper tackles the problem of improving text classification performance with large language models (LLMs) by proposing the Code Completion Prompt (CoCoP) method, which transforms text classification into a code completion task, resulting in enhancements such as over 20% accuracy gain on the SST2 dataset and competitive performance with smaller model sizes.
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.