Google Research: A new technique for determining relevance.

By Marie Haynes
1 min read

Table of Contents

This recent Google paper talks about building better information retrieval models by using synthetic data. This is done using a new method called pairwise query generation. 

They give an LLM a document and ask it to generate two queries. One of the queries is relevant and the other is irrelevant. Doing this encourages the model to learn the difference between a relevant and an irrelevant match. 

In other words, focusing on what makes one query relevant and another not relevant teaches the model how to understand more about what makes something relevant to a query.

What’s the point? This method of training models to better understand relevance could significantly improve the quality of Google search. It’s expected to be especially useful for new topics or search queries Google has not seen before.

What does this mean for SEO? This technique should help Google’s systems get even better at understanding user intent and which content meets that intent. It will become even more important for us to deeply understand and meet the needs of our audience.

🤖
How was AI used in creating this post? This post was written by me, Marie, a human. However, I spent a few hours with NotebookLM discussing and understanding this paper. The image was created with Grok with the prompt, "Make an image of a robot holding up two pieces of paper. One says relevant and the other says not relevant."

This originally started off as an entry in Marie's Notes. It was interesting enough for me to publish it as a full article!

Tagged in:

Research, Search

Last Update: November 15, 2024

About the Author

Marie Haynes

I love learning and sharing about AI. Formerly a veterinarian, in 2008, understanding Google search algorithms captivated me. In 2022 my focus shifted to understanding AI. AI is the future!

View All Posts