arXiv cs.CL· Lucen Li, Erin Wertz, Muhammad Haroon, Anshuman Chhabra, Magdalena Wojcieszak·· 10 小时前AI 评分39
用 LLM 智能体评估社交媒体平台上的亲社会干预
Using LLM Agents to Evaluate Prosocial Interventions on Social Media Platforms
AI 导读
研究团队基于 OASIS 框架构建仿真评估流程，生成 13,835 个带独立画像的 LLM 智能体，在 20 余个时间步内接触真实 Twitter/X 帖子并执行评论、点赞、转发、关注等行为，系统评估三种提升可信新闻曝光的干预方式。
正文 · 原文
Abstract:Social media platforms are a primary source of information for many users. Although research explores various interventions to promote prosocial content or demote harmful content on platforms, there are few systematic methods for evaluating competing intervention designs before conducting costly human-subject experiments. We develop a simulation-based evaluation pipeline built on the OASIS framework. We generate 13,835 LLM-based agents, each with a unique profile. Over 20 time steps, we expose them to real-world Twitter/X posts and let them comment, like, repost, or follow. We use those agents to systematically evaluate three interventions that increase exposure to verified news: adding content, upranking content, and celebrity source cues. All interventions significantly increase news engagement, with upranking news to prominent feed positions producing the largest effects. These effects hold across agents' gender, age, and education levels. We validate our injection treatment results against a comparable human-subject study and find strong directional alignment and similar dose-normalized efficiency. Our results suggest that LLM-based agent simulations can support early-stage evaluation of platform interventions before human-subject deployment, and upranking may be more effective than news volume or source.
| Subjects: | Social and Information Networks (cs.SI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.12922 [cs.SI] |
| (or arXiv:2611.12922v1 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.12922 arXiv-issued DOI via DataCite |
Submission history
From: Lucen Li [view email]
[v1]
Sun, 1 Nov 2026 01:24:59 UTC (2,353 KB)
来源：arXiv cs.CL · arxiv.org