Dropbox Tech·unknown·9 min read·
Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura,Mike White,Kevin Altschuler,Facundo Agriel,Ishan Mishra,Eric Wang,Dmitriy Meyerzon,Dmitriy Meyerzon
57
Using LLMs to amplify human labeling and improve Dash search relevance
How we train Dash's search ranking models with a mix of human and LLM-assisted labeling.
Discussion around the web
- Hacker News1 · 0 💬
Score breakdown
- Technical depth53
- Practical value60
- Originality85
- Writing quality100
- Source reputation85
- Recency0
- External engagement0
- On-site engagement0
More like this
Etsy — Code as Craft64
How Etsy Uses LLMs to Improve Search Relevance
Yuqing Zhang·unknown·10 min read
Etsy — Code as Craft64
Making Ads Count: Using MMoE and Auxiliary Tasks to Better Connect Buyers & Sellers
Amanda Steigman·unknown·11 min read
Engineering at Meta54
From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
unknown·7 min read
Yelp Engineering26
Building Biz Ask Anything: From Prototype to Product
Maria Christoforaki, Group Tech Lead; Shree Shalini Pusapati, Software Engineer
·unknown·1 min read
Engradar shows a summary and links to the original article. The full article is hosted on dropbox.tech.