Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910853126684672 |
|---|---|
| author | Glazkova, Anna Zakharova, Olga |
| author_facet | Glazkova, Anna Zakharova, Olga |
| contents | Large language models (LLMs) play a crucial role in natural language processing (NLP) tasks, improving the understanding, generation, and manipulation of human language across domains such as translating, summarizing, and classifying text. Previous studies have demonstrated that instruction-based LLMs can be effectively utilized for data augmentation to generate diverse and realistic text samples. This study applied prompt-based data augmentation to detect mentions of green practices in Russian social media. Detecting green practices in social media aids in understanding their prevalence and helps formulate recommendations for scaling eco-friendly actions to mitigate environmental issues. We evaluated several prompts for augmenting texts in a multi-label classification task, either by rewriting existing datasets using LLMs, generating new data, or combining both approaches. Our results revealed that all strategies improved classification performance compared to the models fine-tuned only on the original dataset, outperforming baselines in most cases. The best results were obtained with the prompt that paraphrased the original text while clearly indicating the relevant categories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_14896 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts Glazkova, Anna Zakharova, Olga Computation and Language Computers and Society Social and Information Networks 68T50 I.2.7; J.4; I.7.2 Large language models (LLMs) play a crucial role in natural language processing (NLP) tasks, improving the understanding, generation, and manipulation of human language across domains such as translating, summarizing, and classifying text. Previous studies have demonstrated that instruction-based LLMs can be effectively utilized for data augmentation to generate diverse and realistic text samples. This study applied prompt-based data augmentation to detect mentions of green practices in Russian social media. Detecting green practices in social media aids in understanding their prevalence and helps formulate recommendations for scaling eco-friendly actions to mitigate environmental issues. We evaluated several prompts for augmenting texts in a multi-label classification task, either by rewriting existing datasets using LLMs, generating new data, or combining both approaches. Our results revealed that all strategies improved classification performance compared to the models fine-tuned only on the original dataset, outperforming baselines in most cases. The best results were obtained with the prompt that paraphrased the original text while clearly indicating the relevant categories. |
| title | Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts |
| topic | Computation and Language Computers and Society Social and Information Networks 68T50 I.2.7; J.4; I.7.2 |
| url | https://arxiv.org/abs/2411.14896 |