# A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection

arXiv: https://arxiv.org/abs/2604.26319 · HTML: https://mlsanity.com/paper/2604.26319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 6 of 6)

- [Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations](https://mlsanity.com/paper/2010.03640/) (2020)
- [How would Stance Detection Techniques Evolve after the Launch of ChatGPT?](https://mlsanity.com/paper/2212.14548/) (2022)
- [Stance Detection with Collaborative Role-Infused LLM-Based Agents](https://mlsanity.com/paper/2310.10467/) (2023)
- [A Survey of Stance Detection on Social Media: New Directions and Perspectives](https://mlsanity.com/paper/2409.15690/) (2024)
- [C-MTCSD: A Chinese Multi-Turn Conversational Stance Detection Dataset](https://mlsanity.com/paper/2504.09958/) (2025)
- [Is External Information Useful for Stance Detection with LLMs?](https://mlsanity.com/paper/2507.01543/) (2025)

## Abstract (arXiv)

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.