AI Dynamics

Global AI News Aggregator

About

New Research: SFT+RL Pipeline Boosts Search-Augmented AI Accuracy

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.

→ View original post on X — @perplexity_ai,