Using Large Language Models as Recommendation Systems

<p>Large Language Models (LLMs) have taken the data science community and the news cycle by storm these past few months. Since the advent of the transformer architecture in 2017, we&rsquo;ve seen exponential advancements in the complexity of natural language tasks that these models can tackle from classification, to intent &amp; sentiment extraction, to generating text eerily similar to humans.</p> <p>From an application standpoint, the possibilities seem endless when combining LLMs with various existing technologies, to cover their pitfalls (one of my favorite being the&nbsp;<a href="https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its-wolfram-superpowers/" rel="noopener ugc nofollow" target="_blank">GPT + Wolfram Alpha combo</a>&nbsp;to handle math and symbolic reasoning problems).</p> <p><a href="https://towardsdatascience.com/using-large-language-models-as-recommendation-systems-49e8aeeff29b"><strong>Website</strong></a></p>