@_weiping : Introducing RankRAG, a novel RAG framework that instruction-tunes a single LLM for the dual purposes of top-k context ranking and answer generation in RAG. For context ranking, it performs exceptionally well by incorporating a small fraction of ranking data into the training • TwiCopy

Wei Ping

@_weiping

+ Follow

Distinguished Research Scientist @NVIDIA, working on large language models.
Views my own.

ID: 1273059094325153793

linkhttps://wpingnet.github.io/ calendar_today17-06-2020 01:05:33

271 Tweet

2,2K Followers

287 Following

Wei Ping

@_weiping

a year ago

Introducing RankRAG, a novel RAG framework that instruction-tunes a single LLM for the dual purposes of top-k context ranking and answer generation in RAG. For context ranking, it performs exceptionally well by incorporating a small fraction of ranking data into the training

$Introducing RankRAG, a novel RAG framework that instruction-tunes a single LLM for the dual purposes of top-k context ranking and answer generation in RAG. For context ranking, it performs exceptionally well by incorporating a small fraction of ranking data into the training$

thumb_up_off_alt152

chat_bubble_outline3

repeat38

shareShare