DEEM: Dynamic Experienced Expert Modeling for Stance Detection
This addresses the problem of improving stance detection accuracy for applications requiring domain knowledge, though it is incremental over existing multi-agent approaches.
The paper tackles stance detection by proposing DEEM, a method that uses large language models to generate dynamic expert agents for more accurate analysis, achieving state-of-the-art results on three benchmarks and reducing model bias.
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.