LLMs are all the rage these days...
|Illustration by DALL-E of a medical scientist doing research|
Some studies show that office workers who use LLMs (e.g., Google's Bard or OpenAI's ChatGPT) are more productive... on the tasks that they measured. (At least that's MIT's department of economics conclusion.)
And it's pretty clear that LLMs and associated generative AI tools (see the illustration above) can come in pretty handy when given decent prompts.
Our SearchResearch Challenge for this week is an open-ended Challenge. For these Challenges, I usually know what the "right" answer is and how to find it.
But this week, this really is a call for the SRS community to help identify ways of using LLMs to do a very specific kind of research--a kind that we care a lot about--medical research. Here's the Challenge for the week:
1. What good advice can we give a person who wants to use an LLM for high-stakes research into a medical question? We know people are doing this, and all of our ranting about LLMs won't stop them--but can we find ways of using LLMs and specific LLM/AI tools to improve the search process? What would you say to people who are doing this? (Aside from "be very, very careful.")
Maybe the point of using an LLM in "medical research" mode is just to help us to find really great search terms to use in regular web-search. I'm not sure. But if so, let's figure that out. Are there other ways of using LLMs to get better results faster? Or will the search for truth in LLMs be a bust?
I'm focusing on medical research because it is high stakes, it's not okay to just skate on past little errors and unfortunate phrasing.
A big problem here is that most of us are not medical experts, so it's going to be difficult to validate what the LLM tells you.
My suggestion: Try doing a few medical search tasks in a medical area that you know something about. Nearly everyone has been forced to become a mini-expert in some medical area. I'm a mini-expert in a couple of really unusual types of cancer (family members, not me!) when I had to learn enough to make good recommendations to them. So I can explore what an LLM tells me about that with some confidence that I'll have a basic understanding of an esoteric area.
I'll be leaving comments in the thread this week (more than usual) as I work on this question as well.
Let's figure out what advice we can give to LLM users.
When you write your comments in the thread, be sure to tell us which LLMs you've been using. (There are a lot of them out there, all with very different behaviors. Let's be sure to keep our results limited appropriately.)
And be sure to include the search path you followed (which now will include LLM prompts). Mention the dead ends you found and strategies that just don't seem to work. Negative results are really important here!