Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs
TL;DR
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.
Abstract
Stance detection requires identifying an author's attitude toward a given target, sometimes based on conversational context. Jev, a specialized decision model designed for structured decision-making, offers an alternative to general-purpose large language models (LLMs). In this work, we evaluate Jev on two stance detection datasets, VAST (English texts) and ZS-CSD (Chinese conversations), comparing it with four general-purpose LLMs and two fine-tuned models. Results show that Jev achieves competitive performance on VAST, matching GPT-5.6 and outperforming the other general-purpose LLMs. However, it falls behind stronger LLMs on ZS-CSD, particularly in distinguishing favor from against. Further analysis suggests that this limitation may be related to understanding reply relationships and stance direction rather than conversation length alone. These findings highlight both the potential and limitations of Jev for stance detection.
