在线阴谋论的智能体检测
Agentic Detection of Online Conspiracies
- Ben-Gurion University of the Negev（内盖夫本-古里安大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出一个智能体框架，利用社会上下文和工具推理，在希伯来语推文中检测阴谋论意图，显著优于文本分类及其他模型。
AI中文摘要：
社交媒体上的阴谋论话语并不总是通过明确的声明或稳定的词汇标记来表达。相同的表面内容可能表达赞同、合理关切、批评、讽刺或嘲弄。因此，主要挑战不仅在于识别与阴谋相关的声明，还在于推断说话者的意图——即话语的言外之力。我们认为，这可以通过利用相关的社会背景来实现，并提出了一个配备支持社会查询工具集的智能体框架。我们在一个独特的希伯来语推文数据集上展示了我们方法的优势，该数据集覆盖了四年期间（2018年末至2023年初）公开希伯来语推文的80%至90%，涵盖了多个选举周期以及COVID大流行年份和相关的疫苗接种活动。这种广泛的覆盖可用于恢复不同的社会背景。在一个手动标注的对抗性数据集上评估我们的框架，我们发现上下文感知的工作流程始终优于仅文本分类，并且智能体框架的表现显著优于其他框架和设置，包括一个暴露于智能体可获得的相同上下文的非智能体模型。我们进一步提供了对结果、错误和效率（令牌经济性）权衡的分析。这些发现支持将阴谋检测任务视为一种社会嵌入的解释任务，其中有效的分类不仅依赖于对上下文的访问，还依赖于适应性推理，即智能体在个案基础上使用工具，仅询问与其当前推理步骤相关的证据。
英文摘要：
Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the speaker's intent -- the utterance's illocutionary force. We argue that this can be achieved through the use of relevant social contexts and propose an agentic framework, equipped with a set of tools supporting social queries. We demonstrate the benefits of our approach on a unique dataset of Hebrew tweets, covering 80\%--90\% of the public Hebrew tweets published over a four-year span (late 2018-- early 2023), encompassing several election cycles as well as the COVID pandemic years and related vaccination campaigns. This extensive coverage can be used in recovering different social contexts. Evaluating our framework on a manually-annotated adversarial dataset, we find that context-aware workflows consistently outperform text-only classification and that the agentic framework performs significantly better than other frameworks and settings, including a non-agentic model exposed to the same contexts available to the agent. We further provide an analysis of the results, the errors and efficiency (token economy) tradeoffs. These findings support viewing the task of conspiracy detection as a socially embedded interpretation task, in which effective classification depends not only on access to contexts, but also on adaptive reasoning in which the agent uses tools on a per-case basis, asking only for evidence relevant to its current reasoning step.
