AI RESEARCH
A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection
arXiv CS.CL
•
ArXi:2604.26319v1 Announce Type: new Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task, from zero-shot prompting to multi-agent debate. However, existing works differ in data splits, base models, and evaluation protocols, making fair comparison difficult.