Users want to know if a document is about the searched for terms. Search tech news articles for “iPhone” - relevance statistics like BM25 infer more occurrences in the article body means the article is more about iPhone.

Human authors write more than paragraphs. They add titles and create section headings. Repeated occurrences of a term here rarely matter. There’s no difference between:

  • iPhone for the iPhone expert
  • iPhone: the ultimate guide

So today’s tip, remove the influence of term frequency when searching title fields. you can

  • Lower k1 to 0 to create binary relevance
  • Use an alternative similarity
  • Disable term frequency entirely for this field

-Doug

Services: Training (use code search-tips) · Consulting

This is part of Doug’s Daily Search tips - subscribe here


Enjoy softwaredoug in training course form!

Starting June 22!

I hope you join me at Cheat at Search with LLMs to learn how to apply LLMs to search applications. Check out this post for a sneak preview.

Doug Turnbull

More from Doug
Twitter | LinkedIn | Newsletter | Bsky
Take My New Course - Cheat at Search with LLMs