DEEM: Dynamic Experienced Expert Modeling for Stance Detection

TL;DR

This paper introduces DEEM, a novel method that enhances stance detection by dynamically modeling expert agents within large language models, improving accuracy and reducing bias through semi-parametric reasoning.

Contribution

DEEM is the first approach to dynamically generate and leverage experienced experts within LLMs for stance detection, surpassing existing multi-agent methods.

Findings

DEEM achieves state-of-the-art results on three benchmarks.

It outperforms self-consistency reasoning methods.

It reduces bias in LLM-based stance detection.

Abstract

Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results. However, considering that stance detection usually requires detailed background knowledge, the vanilla reasoning method may neglect the domain knowledge to make a professional and accurate analysis. Thus, there is still room for improvement of LLMs reasoning, especially in leveraging the generation capability of LLMs to simulate specific experts (i.e., multi-agents) to detect the stance. In this paper, different from existing multi-agent works that require detailed descriptions and use fixed experts, we propose a Dynamic Experienced Expert Modeling (DEEM) method which can leverage the generated experienced experts and let LLMs reason in a semi-parametric way, making the experts more generalizable and reliable. Experimental results demonstrate that DEEM consistently achieves the best results on three standard benchmarks, outperforms methods with self-consistency reasoning, and reduces the bias of LLMs.