ChatEL: Entity Linking with Chatbots

TL;DR

ChatEL introduces a three-step prompting framework for Large Language Models to improve Entity Linking accuracy, outperforming traditional models and revealing potential label inaccuracies in datasets.

Contribution

The paper presents a novel three-step prompt-based framework, ChatEL, that enhances LLM-based entity linking performance across multiple datasets.

Findings

ChatEL improves average F1 by over 2% across 10 datasets.

Many ground truth labels are incorrect, with ChatEL's predictions often being correct.

The approach is open-source and easily applicable to various datasets.

Abstract

Entity Linking (EL) is an essential and challenging task in natural language processing that seeks to link some text representing an entity within a document or sentence with its corresponding entry in a dictionary or knowledge base. Most existing approaches focus on creating elaborate contextual models that look for clues the words surrounding the entity-text to help solve the linking problem. Although these fine-tuned language models tend to work, they can be unwieldy, difficult to train, and do not transfer well to other domains. Fortunately, Large Language Models (LLMs) like GPT provide a highly-advanced solution to the problems inherent in EL models, but simply naive prompts to LLMs do not work well. In the present work, we define ChatEL, which is a three-step framework to prompt LLMs to return accurate results. Overall the ChatEL framework improves the average F1 performance across 10 datasets by more than 2%. Finally, a thorough error analysis shows many instances with the ground truth labels were actually incorrect, and the labels predicted by ChatEL were actually correct. This indicates that the quantitative results presented in this paper may be a conservative estimate of the actual performance. All data and code are available as an open-source package on GitHub at https://github.com/yifding/In_Context_EL.