Irfan Shuttari of Veritas says the use of large language models (LLMs) and generative AI (GAI) will kill the use of keyword search in eDiscovery!
“No way!”, you say? He says yes, and he discusses several reasons in his post titled The End of “Search” is Upon Us! (available here) why he thinks keyword search will be replaced by LLMs/GAI, not just in eDiscovery, but even eventually in society. Here’s one reason.
You probably already know that generative AI has exploded on the scene in the business world and society. According to the latest available data, ChatGPT currently has around 180.5 million users and OpenAI’s website generated 1.6 billion visits in December 2023. Not only that, but the use of generative AI has extended to web browsing and searching as well. Microsoft Bing has added a GPT-4 Chat capability to its search engine. And Google is expected to do the same with its new Gemini AI model. Searching on the Web is quickly evolving to leverage these exciting new AI capabilities, changing the way we interact with them from a form of keyword searching to a “chat” to find what we need.
So, how does the ubiquity of LLMs and Generative AI extend to legal tech and eDiscovery? And what are three advantages of LLMs/GAI over keyword searching in eDiscovery? Find out here, it’s only one click! You won’t need a keyword search to get there, a simple click will do! 😉
So, what do you think? Will keyword search in eDiscovery be killed by LLMs and GAI? Please share any comments you might have or if you’d like to know more about a particular topic.
Image created using Bing Image Creator Powered by DALL-E, using the term “robot conducting a web search on a smartphone”.
Disclosure: Veritas is an Educational Partner and sponsor of eDiscovery Today
Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.
Discover more from eDiscovery Today by Doug Austin
Subscribe to get the latest posts sent to your email.
I don’t think the writer understands that GenAI models can’t, of themselves, search across large document sets. And having them review every document as an alternative to using a search engine seems expensive and time consuming to me.
Search terms infer that any document talking about particular concepts will include specific words. That’s a falsehood. I can talk about Boston Red Sox baseball all afternoon and never use any of those terms.
But they’d be the first words someone would propose.
I think the author above doesn’t understand that GenAI can, of itself, search across large data sets and the ability for these models to review documents at some multiple of human ability with full documentation of why a tag was selected or not is reality.
The limitations of AI are more related to the current state of the art than what this kind of tech is capable of. I expect to see significant growth in application of GenAI in document review.
Kindest regards,
Dave