智能科学与技术学报2025，Vol.7Issue(4)：517-532,16.DOI:10.11959/j.issn.2096-6652.202545
大模型驱动的社交智能体谣言易感性与干预策略研究
Rumor susceptibility and intervention strategies of large language model-driven social agents
摘要
Abstract
In recent years,numerous social agents empowered by large language model(LLM)have emerged on social media,which play a significant role in online social interactions.However,since not all messages shared on social media are verified as genuine,the involvement of these agents could amplify rumor propagation.Therefore,it becomes increas-ingly important to measure agents'susceptibility to rumors and reduce their acceptance of rumors.To tackle this issue,agents'susceptibility to rumors and how their opinion evolve on social media were systematically examined.The findings demonstrate that agents are highly susceptible to unknown rumors,tend to reinforce their beliefs over time through pro-longed exposure.Furthermore,agents show a strong tendency to believe rumors during social interactions.To reduce agents'susceptibility to rumors,a"self-prompting"intervention strategy was proposed,which significantly reduced ru-mor acceptance rate among agents from 75.91%to 13.50%and effectively motivated agents with a neutral stance to take on anti-rumor positions.This research not only deepens our understanding of the mechanisms behind the rumor suscepti-bility of LLM-driven agents,but also provides an effective pathway to improve their anti-rumor capabilities,thereby offer-ing support for the safe deployment of agents on social media and reduction of rumor propagation.关键词
大语言模型/社交智能体/谣言易感性分析/谣言干预策略Key words
large language model/social agent/rumor susceptibility/rumor intervention分类
信息技术与安全科学引用本文复制引用
殷勇杰,袁靖炜,宫庆媛,陈阳..大模型驱动的社交智能体谣言易感性与干预策略研究[J].智能科学与技术学报,2025,7(4):517-532,16.基金项目
国家自然科学基金项目(No.62102094) The National Natural Science Foundation of China(No.62102094) （No.62102094）
