Parametric Social Identity Injection and Diversification in Public Opinion Simulation 文章

ArXiv CS.CL2026-06-02NEWSen作者: Hexi Wang, Yujia Zhou, Bangde Du, Qingyao Ai, Yiqun Liu

摘要

arXiv:2603.16142v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despite their scalability, current LLM-based simulation methods fail to capture social diversity, producing flattened inter-group differences and overly homogeneous responses across demographic groups. We identify this limitation as a Diversity Collapse phenomenon in LLM hidden representations, where distinct social identities become increasingly indistinguishable across layers. Motivated by this observation, we propose Parametric Social Identity Injection (PSII), a general framework that injects explicit, parametric representations of demographic attributes and value orientations directly into intermediate hidden states of LLMs. Unlike prompt-based persona conditioning, PSII enables fine-grained and controllable identity modulation at the representation level.

相关事件查看全部 (1)

相关公司

暂无数据

相关人物

暂无数据

相关产品

暂无数据