用微博环境测试大模型代理是否真实响应信息负载与社会规范
Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues
- 在模拟微博环境中操控信息量与描述性规范
- 代理行为随信息负载和规范变化，对热门度反应具情境依赖性
- 适合做传播机制研究的仿真方法论参考
大语言模型让基于代理的模拟更具行为表现力，但也加剧了基本方法论矛盾：流畅的人类化输出本身并非理论证据。本文以社交媒体上的信息参与度为案例，评估基于LLM的模拟能可信支持什么结论。在类微博环境中，我们操纵信息负载和描述性规范，同时允许热度线索（累计点赞数与转发数）内生演化。结果表明，参与度系统性响应信息负载与描述性规范，对流行度线索的敏感性因情境而异，体现条件性而非机械遵循提示。本文讨论了仿真研究的方法论启示，包括多条件压力测试、明确无规范基线（因默认提示非空白控制），以及在研究从众动态时保持内生反馈环的设计选择。
原文摘要 · Abstract (English)
Large language models make agent-based simulation more behaviorally expressive, but they also sharpen a basic methodological tension: fluent, human-like output is not, by itself, evidence for theory. We evaluate what an LLM-driven simulation can credibly support using information engagement on social media as a test case. In a Weibo-like environment, we manipulate information load and descriptive norms, while allowing popularity cues (cumulative likes and Sina Weibo-style cumulative reshares) to evolve endogenously. We then ask whether simulated behavior changes in theoretically interpretable ways under these controlled variations, rather than merely producing plausible-looking traces. Engagement responds systematically to information load and descriptive norms, and sensitivity to popularity cues varies across contexts, indicating conditionality rather than rigid prompt compliance. We discuss methodological implications for simulation-based communication research, including multi-condition stress tests, explicit no-norm baselines because default prompts are not blank controls, and design choices that preserve endogenous feedback loops when studying bandwagon dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。