Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915144346370048 |
|---|---|
| author | Du, Shaoshuai Tao, Yiyi Shen, Yixian Zhang, Hang Shen, Yanxin Qiu, Xinyu Shi, Chuanqi |
| author_facet | Du, Shaoshuai Tao, Yiyi Shen, Yixian Zhang, Hang Shen, Yanxin Qiu, Xinyu Shi, Chuanqi |
| contents | This study investigates the performance of various large language models (LLMs) on zero-shot end-to-end relation extraction (RE) in Chinese, a task that integrates entity recognition and relation extraction without requiring annotated data. While LLMs show promise for RE, most prior work focuses on English or assumes pre-annotated entities, leaving their effectiveness in Chinese RE largely unexplored. To bridge this gap, we evaluate ChatGPT, Gemini, and LLaMA based on accuracy, efficiency, and adaptability. ChatGPT demonstrates the highest overall performance, balancing precision and recall, while Gemini achieves the fastest inference speed, making it suitable for real-time applications. LLaMA underperforms in both accuracy and latency, highlighting the need for further adaptation. Our findings provide insights into the strengths and limitations of LLMs for zero-shot Chinese RE, shedding light on trade-offs between accuracy and efficiency. This study serves as a foundation for future research aimed at improving LLM adaptability to complex linguistic tasks in Chinese NLP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05694 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT Du, Shaoshuai Tao, Yiyi Shen, Yixian Zhang, Hang Shen, Yanxin Qiu, Xinyu Shi, Chuanqi Computation and Language Artificial Intelligence Machine Learning This study investigates the performance of various large language models (LLMs) on zero-shot end-to-end relation extraction (RE) in Chinese, a task that integrates entity recognition and relation extraction without requiring annotated data. While LLMs show promise for RE, most prior work focuses on English or assumes pre-annotated entities, leaving their effectiveness in Chinese RE largely unexplored. To bridge this gap, we evaluate ChatGPT, Gemini, and LLaMA based on accuracy, efficiency, and adaptability. ChatGPT demonstrates the highest overall performance, balancing precision and recall, while Gemini achieves the fastest inference speed, making it suitable for real-time applications. LLaMA underperforms in both accuracy and latency, highlighting the need for further adaptation. Our findings provide insights into the strengths and limitations of LLMs for zero-shot Chinese RE, shedding light on trade-offs between accuracy and efficiency. This study serves as a foundation for future research aimed at improving LLM adaptability to complex linguistic tasks in Chinese NLP. |
| title | Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.05694 |