DEEM: Dynamic Experienced Expert Modeling for Stance Detection

arXiv:2402.15264v1 Announce Type: new
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 …

abstract arxiv cs.cl detection domain domain knowledge dynamic expert knowledge language language models large language large language models llms modeling professional reasoning results solve type work