位置：逻辑正确性不是LLM神经符号事实核查中的可靠标准
Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs
AI总结：
本文指出，逻辑正确性无法有效检测误导性声明，提出利用LLM的人类推理倾向来验证神经符号系统中的正式组件输出。
摘要：
随着大型语言模型（LLMs）越来越多地集成到事实核查流程中，形式逻辑常被提出作为严谨的手段，以缓解这些模型输出中的偏见、错误和幻觉。例如，一些神经符号系统通过使用LLMs将自然语言翻译成逻辑公式，然后检查提出的声明是否在逻辑上成立，即是否能从已被验证为真的前提中有效推导出来。我们主张，此类方法在结构上无法检测误导性声明，因为逻辑上成立的结论与人类通常做出的推理之间存在系统性差异。基于认知科学和语用学的研究，我们提出了几种情况的分类，其中逻辑上成立的结论系统性地引发人类无法由基础前提支持的推理。因此，我们倡导一种互补的方法：利用LLM的人类推理倾向作为特征而非缺陷，并利用这些模型验证神经符号系统中正式组件输出的潜在误导性结论。
英文摘要：
As large language models (LLMs) are increasing integrated into fact-checking pipelines, formal logic is often proposed as a rigorous means by which to mitigate bias, errors and hallucinations in these models' outputs. For example, some neurosymbolic systems verify claims by using LLMs to translate natural language into logical formulae and then checking whether the proposed claims are logically sound, i.e. whether they can be validly derived from premises that are verified to be true. We argue that such approaches structurally fail to detect misleading claims due to systematic divergences between conclusions that are logically sound and inferences that humans typically make and accept. Drawing on studies in cognitive science and pragmatics, we present a typology of cases in which logically sound conclusions systematically elicit human inferences that are unsupported by the underlying premises. Consequently, we advocate for a complementary approach: leveraging human-like reasoning tendencies of LLMs as a feature rather than a bug, and using these models to validate the outputs of formal components in neurosymbolic systems against potentially misleading conclusions.
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。
