Helping Searchers Satisfice through Query Understanding

This morning, I had the opportunity to present an invited talk at Walmart’s AI Summit. Not surprisingly, a lot of folks were excited about the potential of ChatGPT, GPT-4, and LLMs in general.

I decided to do something a little different. Here is my abstract:

Behavioral economics transformed how we think about human decision making, rejecting expected utility maximization for the real world of heuristics, biases, and satisficing. In this talk, I’ll argue that our thinking about search engines needs a similar transformation. I will compare the Probability Ranking Principle to expected utility maximization and offer ways that AI can help searchers satisfice through query understanding.

I hope the audience enjoyed it, and I hope you all enjoy the slides below!