Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs
Evaluated Jev on two stance detection datasets, VAST and ZS-CSD, shows competitive performance on VAST, matching GPT-5.6 and outperforming the other general-purpose LLMs, but falls behind stronger LLMs on ZS-CSD, particularly in distinguishing favor from against.
Xing Li, Jin-Zhong Ning, Yi-Jia Zhang et al.
· 0 citations