A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection
Provides a fair, large-scale benchmark for practitioners choosing between prompting and multi-agent strategies for stance detection.
The paper systematically compares prompt-based and multi-agent methods for LLM-based stance detection across 14 subtasks, 15 LLMs, and 4 datasets, finding that prompt-based methods outperform agent-based methods while requiring 7-12 times fewer API calls, and that model scale impacts performance more than method choice.
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. We conduct a systematic comparison that evaluates five methods across two categories -- prompt-based inference (Direct Prompting, Auto-CoT, StSQA) and agent-based debate (COLA, MPRF) -- on four datasets with 14 subtasks, using 15 LLMs from six model families with parameter sizes from 7B to 72B+. Our experiments yield several findings. First, on all models with complete results, the best prompt-based method outperforms the best agent-based method, while agent methods require 7 to 12 times more API calls per sample. Second, model scale has a larger impact on performance than method choice, with gains plateauing around 32B. Third, reasoning-enhanced models (DeepSeek-R1) do not consistently outperform general models of the same size on this task.