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 2405.07417cs.SIeess.SP
收藏

识别在线平台中的仇恨言论散布者:面向大语言模型驱动决策者的贝叶斯社会学习方法

Identifying Hate Speech Peddlers in Online Platforms. A Bayesian Social Learning Approach for Large Language Model Driven Decision-Makers

Adit Jain, Vikram Krishnamurthy

AI总结:

针对LLM辅助的自主贝叶斯检测器,本文研究高维文本观测下的序贯社会学习,证明有限时间羊群效应,并提出最优停时与阈值策略以平衡隐私和 herd 行为。

摘要:

本文研究自主智能体在状态观测属于高维空间且分析成本高昂时,执行贝叶斯社会学习以进行序贯检测的问题。具体而言,当观测为文本时,贝叶斯智能体可使用大语言模型(LLM)作为映射,以获得低维私有观测。智能体执行贝叶斯学习,并采取使期望成本最小化、且对后续智能体可见的行动。我们证明,此类贝叶斯智能体序列会在有限时间内围绕公共信念形成羊群效应,并采取相同行动,而无视各自的私有观测。我们提出了一种用于社会学习中最快时间羊群效应的停时表述,并在隐私与羊群效应之间实现最优平衡。结构结果表明,停时问题的最优策略具有阈值性质。我们通过如下场景说明该框架的应用:自主贝叶斯检测器利用LLM解析文本观测,旨在序贯识别某一用户是否为在线平台上的仇恨言论散布者。我们在真实世界仇恨言论数据集上对结果进行了数值验证。结果表明,当公共先验较强时,被设计用于标记在线平台仇恨言论散布者的自主贝叶斯智能体会发生羊群效应并错误分类用户。我们还通过数值方式展示了阈值策略在延迟羊群效应方面的作用。

英文摘要:

This paper studies the problem of autonomous agents performing Bayesian social learning for sequential detection when the observations of the state belong to a high-dimensional space and are expensive to analyze. Specifically, when the observations are textual, the Bayesian agent can use a large language model (LLM) as a map to get a low-dimensional private observation. The agent performs Bayesian learning and takes an action that minimizes the expected cost and is visible to subsequent agents. We prove that a sequence of such Bayesian agents herd in finite time to the public belief and take the same action disregarding the private observations. We propose a stopping time formulation for quickest time herding in social learning and optimally balance privacy and herding. Structural results are shown on the threshold nature of the optimal policy to the stopping time problem. We illustrate the application of our framework when autonomous Bayesian detectors aim to sequentially identify if a user is a hate speech peddler on an online platform by parsing text observations using an LLM. We numerically validate our results on real-world hate speech datasets. We show that autonomous Bayesian agents designed to flag hate speech peddlers in online platforms herd and misclassify the users when the public prior is strong. We also numerically show the effect of a threshold policy in delaying herding.

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。

↑