EntGPT: Entity Linking with Generative Large Language Models
This work addresses entity linking for NLP researchers and practitioners, offering a method that is incremental but effective in enhancing LLM-based approaches.
The paper tackled the problem of entity linking in NLP by introducing EntGPT, which uses advanced prompt engineering to improve performance, achieving up to a 36% boost in micro-F1 scores over vanilla prompts and competitive results across 10 datasets without fine-tuning.
Entity Linking in natural language processing seeks to match text entities to their corresponding entries in a dictionary or knowledge base. Traditional approaches rely on contextual models, which can be complex, hard to train, and have limited transferability across different domains. Generative large language models like GPT offer a promising alternative but often underperform with naive prompts. In this study, we introduce EntGPT, employing advanced prompt engineering to enhance EL tasks. Our three-step hard-prompting method (EntGPT-P) significantly boosts the micro-F_1 score by up to 36% over vanilla prompts, achieving competitive performance across 10 datasets without supervised fine-tuning. Additionally, our instruction tuning method (EntGPT-I) improves micro-F_1 scores by 2.1% on average in supervised EL tasks and outperforms several baseline models in six Question Answering tasks. Our methods are compatible with both open-source and proprietary LLMs. All data and code are available on GitHub at https://github.com/yifding/In_Context_EL.