Locating Sycophancy Across Training Stages in Open Language Models
arXiv:2610.37788v1 Announce Type: new Abstract: Language model assistants sometimes change a correct answer when the user suggests a wrong one. The behavior, called sycophancy, is usually attributed to preference-based post-training, yet early measurements found it in pretrained models. We ask where
Der Artikeltext wird beim nächsten Sync nachgeladen. Original bei arXiv cs.CL lesen
Quelle: arXiv cs.CL (arXiv cs.CL). Original öffnen