TE
TechEcho
Home
24h Top
Newest
Best
Ask
Show
Jobs
English
GitHub
Twitter
Home
Discover the Performance Gain of LLMs with Retrieval Augmented Generation
1 points
by
Bella-Xiang
over 1 year ago
1 comment
LukeAI
over 1 year ago
Interesting results: combining Llama-13B with Wikipedia backed by a vector database can reduce hallucination, and significantly improves its performance on MMLU scores.