Airbnb Introduces CASTLE Framework for Training Natural Language Search Models with Synthetic Data
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
Airbnb researchers introduced CASTLE, a framework addressing the cold-start problem in natural language search by using de-identified booking sessions and large language models to generate synthetic training data.
Read the full story at InfoQ AI/ML ↗
Timeline · 1 report
- 2026-11-16 12:25 · InfoQ AI/ML
Airbnb Introduces CASTLE for Training Natural Language Search Models with Synthetic Data