{"id":79339,"date":"2024-04-18T09:00:24","date_gmt":"2024-04-18T08:00:24","guid":{"rendered":"https:\/\/www.bullhorn.com\/uk\/?post_type=customer_blog&p=79339"},"modified":"2024-09-20T18:01:06","modified_gmt":"2024-09-20T17:01:06","slug":"what-to-consider-when-choosing-an-llm","status":"publish","type":"customer_blog","link":"https:\/\/www.bullhorn.com\/uk\/customer-blog\/what-to-consider-when-choosing-an-llm\/","title":{"rendered":"What to consider when choosing an LLM"},"content":{"rendered":"

Bullhorn Copilot is now called Bullhorn AI. For more on our AI strategy, visit\u00a0bullhorn.com\/ai<\/a>.<\/em><\/p>\n

\n

Copilot is here<\/span><\/a>, and our customers are already <\/span>hitting the ground running with recruitment AI<\/span><\/a>. As agencies embark upon their generative AI journeys and incorporate Copilot into their workflows, one of their most frequently asked questions is, <\/span>\u201cWhich LLM (Large Language Model) should I choose to integrate with Copilot?\u201d<\/b><\/p>\n

There\u2019s no one right answer; which LLM is best for you and your team depends on your business goals and what you want to achieve with Copilot. Regardless of your decision, you\u2019ll still be able to leverage generative AI to craft stronger messages, send more pitches, and generate profile summaries, screening questions, and more \u2014 all without leaving Bullhorn.\u00a0<\/span><\/p>\n

Let\u2019s break down what an LLM is, which LLMs integrate with Copilot, what the Bullhorn experts have to say about LLMs, and how you can decide which one is right for your recruitment business.<\/span><\/p>\n

What is an LLM?<\/strong><\/h3>\n

An LLM is a deep learning model that has been pre-trained on vast amounts of data and is used to power generative AI.<\/span><\/p>\n

LLMs use <\/span>tokens<\/b> to understand and respond to prompts. They can be thought of as pieces of words, though they also include spaces and punctuation marks; each one is roughly four characters of typical English text. When you ask AI a question, it looks at each token \u2013 that is, each word, space, and piece of punctuation \u2013 to understand and respond to your question. You can learn more about tokens \u2013 and how to count them \u2013 <\/span>here<\/span><\/a>. Different LLMs also have different token limits, which limit the length of the prompt you input and the response the LLM generates; a shorter token limit means that you\u2019ll need to input shorter prompts.<\/span><\/p>\n

Why do I need to choose an LLM to integrate with Copilot?<\/strong><\/h3>\n

\u201cCopilot is the vehicle through which users access what the LLM can do,\u201d said Nicole Krensky, Director of Product Marketing, Automation & AI at Bullhorn. <\/span>Once you choose your LLM, you will connect that service with Copilot using an API. Copilot then pushes the information in your database, like candidate resumes, skills, education, and work history, along with the prompt you build or select, to the LLM to generate your desired output.<\/span><\/p>\n

\u201cThink of it as powering the engine in the background,\u201d added Ben Carter, Senior Director, Automation & AI at Bullhorn.<\/span><\/p>\n

Which LLMs integrate with Copilot?<\/strong><\/h3>\n

Bullhorn currently supports <\/span>Azure OpenAI<\/b> and <\/span>OpenAI<\/b> LLMs. Customers have seen success with the following models:\u00a0<\/span><\/p>\n