Can ChatGPT Outperform Other Language Models? An Experiment on Using ChatGPT for Entity Matching Versus Other Language Models

In the era of rising AI, ChatGPT has become the most well-known chatbot, utilizing Large Language Models (LLMs), specifically GPT versions 3.5 or 4. It has been employed in various tasks, including text generation and text summarization. Entity Matching is one such task that requires the comparison of information in the records of interest. Traditionally, this work has relied on rule-based similarity measurements. However, in recent years, novel methods have emerged to combat this problem, including the use of word vectors, neural networks, and language models. In this paper, we will compare the results of the Entity Matching task by using ChatGPT and other language models, such as sentence-BERT and RoBERTa. Additionally, we will compare the results from zero-shot capable models like RoBERTa, DistilBERT, and BART. For the Blocking phase, we will use benchmark datasets that are available in ready-to-use formats, in conjunction with other novel blocking methods, if available.