We've published new research on how we post-train models for accurate search-augmented answers. Our...
- SFT+RL pipeline改善搜索、引用和指令遵循能力。
- 使用Qwen模型在事实性上媲美或超越GPT模型。
- 以更低的成本实现高性能的事实性输出。
Our SFT + RL pipeline improves search, citation quality, instruction following, and efficiency.
With Qwen models, we match or beat GPT models on factuality at a lower cost. https://t.co/0w0Jmc9xlS" / X
Perplexity on X: "We've published new research on how we post-train models for accurate search-augmented answers. Our SFT + RL pipeline improves search, citation quality, instruction following, and efficiency. With Qwen models, we match or beat GPT models on factuality at a lower cost. https://t.co/0w0Jmc9xlS" / X
Don’t miss what’s happening
People on X are the first to know.
Post
See new posts
Conversation
We've published new research on how we post-train models for accurate search-augmented answers. Our SFT + RL pipeline improves search, citation quality, instruction following, and efficiency. With Qwen models, we match or beat GPT models on factuality at a lower cost.
·
41
91
920
423
Read 41 replies
New to X?
Sign up now to get your own personalized timeline!
Sign up with Apple
By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.
Relevant people
-  Perplexity @perplexity_ai Follow Click to Follow perplexity_ai Curiosity changes everything. Download our free app on iOS, Mac, Windows, and Android.
Trending now
What’s happening
Sports · Trending
#BURMCI
Trending in United States
#MichaelMovie!Image 4
Trending in United States
Grapefruit
Politics · Trending
Hung Cao
Trending with Phelan, Secretary of the Navy
|
|
|
|
|
More
© 2026 X Corp.