逻辑严谨不等于可信，大模型推理常被误导
Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs
- 用逻辑验证大模型结论，但人类实际推理方式不同
- 实验发现逻辑上正确结论仍会引发错误人类推断
- 建议将大模型的自然推理当作检测工具而非替代品
随着大语言模型（LLMs）越来越多地融入事实核查流程，形式逻辑常被提出作为减少偏见、错误和幻觉的严格方法。一些神经符号系统利用LLM将自然语言转化为逻辑公式，再检查主张是否在逻辑上成立——即能否从已验证为真的前提中有效推导得出。我们指出，此类方法在结构上无法识别具有误导性的主张，原因在于逻辑上成立的结论与人类通常做出并接受的推论之间存在系统性差异。基于认知科学和语用学研究，我们提出一个分类体系，揭示了在哪些情况下逻辑上正确的结论会系统性地引发人类无法从前提中支持的推论。因此，我们倡导一种互补方法：将大模型的人类式推理倾向视为特征而非缺陷，用这些模型来检验神经符号系统中形式组件输出的结论是否可能具有误导性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。