arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.00371cs.CL
收藏

机器人说了什么?大语言模型在社交媒体机器人检测中的机遇与风险

What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection

University of Washington(华盛顿大学);Xi’an Jiaotong University(西安交通大学);University of Notre Dame(圣母大学)

Shangbin Feng, Herun Wan, Ningnan Wang, Zhaoxuan Tan, Minnan Luo, Yulia Tsvetkov

AI总结:

本文研究大语言模型在社交机器人检测中的双重作用:提出异构专家混合框架构建高性能LLM检测器,同时揭示LLM引导的信息操纵可显著削弱现有检测系统。

摘要:

社交媒体机器人检测一直是机器学习机器人检测技术的进步与对抗性机器人逃避检测策略之间的军备竞赛。在这项工作中,我们将这一军备竞赛推向新的高度,通过研究最先进的大语言模型(LLMs)在社交机器人检测中的机遇与风险。为探究机遇,我们设计了新颖的基于LLM的机器人检测器,提出了一种异构专家混合框架,以分而治之的方式处理多样化的用户信息模态。为揭示风险,我们探索了由LLM引导的用户文本和结构化信息操纵以逃避检测的可能性。在三个LLM和两个数据集上的大量实验表明,仅在1,000个标注样本上进行指令微调即可产生专用LLM,其在两个数据集上的性能均超越最先进的基线,最高提升9.1%;而LLM引导的操纵策略可显著降低现有机器人检测器的性能,降幅最高达29.6%,并损害机器人检测系统的校准性和可靠性。

英文摘要:

Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection. To investigate the opportunities, we design novel LLM-based bot detectors by proposing a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities. To illuminate the risks, we explore the possibility of LLM-guided manipulation of user textual and structured information to evade detection. Extensive experiments with three LLMs on two datasets demonstrate that instruction tuning on merely 1,000 annotated examples produces specialized LLMs that outperform state-of-the-art baselines by up to 9.1% on both datasets, while LLM-guided manipulation strategies could significantly bring down the performance of existing bot detectors by up to 29.6% and harm the calibration and reliability of bot detection systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑