用大模型生成社交机器人网络，发现其行为与真实机器人有明显差异。
Are LLM-Powered Social Media Bots Realistic?
- 结合人工标注、网络科学与大模型生成虚拟机器人及其互动
- 生成的机器人网络在语言和结构上均不同于真实机器人/人类
- 研究结果对识别大模型驱动的社交机器人有重要参考价值
随着大语言模型（LLMs）日益复杂，利用它们驱动社交媒体机器人成为可能。本文通过人工努力、网络科学与大模型相结合的方式，构建了合成的机器人个体角色、其推文及交互行为，从而模拟社交媒体网络。将生成的网络与真实机器人/人类数据进行对比，发现大模型驱动的机器人在网络结构和语言特征上均与真实情况存在差异。这一发现对大模型驱动社交机器人的检测与实际效果评估具有重要意义。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) become more sophisticated, there is a possibility to harness LLMs to power social media bots. This work investigates the realism of generating LLM-Powered social media bot networks. Through a combination of manual effort, network science and LLMs, we create synthetic bot agent personas, their tweets and their interactions, thereby simulating social media networks. We compare the generated networks against empirical bot/human data, observing that both network and linguistic properties of LLM-Powered Bots differ from Wild Bots/Humans. This has implications towards the detection and effectiveness of LLM-Powered Bots.
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。