Here’s a neat paper by Barnett et al. (@DeakinA2I2) that outlines 7 failure points in building a RAG pipeline over your data. 🚫 Missing content (did not index it) 🚫 Missing in top-k retrieved set 🚫 Missing in reranked set 🚫 Not extracted (in context but LLM couldn’t use) 🚫… https://t.co/UvSRBxDL2n https://t.co/nftC9aZ6Jv
— Jerry Liu (@jerryjliu0) Jan 14, 2024
from Twitter https://twitter.com/jerryjliu0
January 14, 2024 at 07:59PM
via IFTTT
No comments:
Post a Comment