How we train Dash's search ranking models with a mix of human and LLM-assisted labeling.
AI Summary
Dropbox's Dash search engine uses a retrieval-augmented generation (RAG) pattern to generate responses, relying on large language models (LLMs) to analyze relevant content and ground responses. To improve search relevance, Dash pairs human labeling with LLM-assisted labeling, starting with a small amount of internal, human-labeled data and then amplifying efforts with LLMs to produce relevance labels at scale. This combination allows Dropbox to train Dash's search ranking models with high-quality labeled examples, resulting in improved search relevance and more accurate responses.
Get the top 10 engineering articles delivered every Monday.