arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.01170cs.CL
收藏

基于人-机器人交互中语言调节特征的机器人文本检测

Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions

University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)

Paras Bhatt, Anthony Rios

摘要:

语言生成模型的民主化使许多领域受益,从回答与健康相关的问题到通过提供人工智能驱动的辅导服务来加强教育。然而,语言生成模型的民主化也使其更容易大规模地生成用于邪恶活动的类人文本,从传播错误信息到针对特定群体的仇恨言论。因此,了解人们如何与机器人交互并开发检测机器人生成的文本的方法至关重要。这篇论文表明,如果我们使用人们如何回应的信息,而不是直接使用机器人的文本,机器人生成的文本检测方法在数据集和模型中更鲁棒。我们还分析了语言对齐,深入了解人与人和人与机器人对话之间的差异。

英文摘要:

Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it easier to generate human-like text at-scale for nefarious activities, from spreading misinformation to targeting specific groups with hate speech. Thus, it is essential to understand how people interact with bots and develop methods to detect bot-generated text. This paper shows that bot-generated text detection methods are more robust across datasets and models if we use information about how people respond to it rather than using the bot's text directly. We also analyze linguistic alignment, providing insight into differences between human-human and human-bot conversations.

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。

↑