独立假设让神经符号模型无法识别某些概念组合的不确定性。
Neurosymbolic Reasoning Shortcuts under the Independence Assumption
- 假设符号概念独立，导致模型无法建模特定组合的不确定性。
- 模型会忽略推理捷径，即正确结果但错误推理路径的现象。
- 对需要可靠推理的场景（如医疗）特别关键，适合关注模型可解释性的人看。
神经符号（NeSy）预测器中普遍采用符号概念间的独立假设，以加速概率推理。尽管近期研究指出该假设会阻碍学习并破坏不确定性建模，但学界对此仍存疑。本文通过形式化证明表明：在独立假设下，模型永远无法表示某些概念组合的不确定性。因此，模型将无法察觉推理捷径——即看似正确但理由错误的病理行为。这揭示了独立假设的根本局限，为理解神经符号系统的行为边界提供了理论基础。
原文摘要 · Abstract (English)
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic reasoning. Recent works like van Krieken et al. (2024) and Marconato et al. (2024) argued that the independence assumption can hinder learning of NeSy predictors and, more crucially, prevent them from correctly modelling uncertainty. There is, however, scepticism in the NeSy community around the scenarios in which the independence assumption actually limits NeSy systems (Faronius and Dos Martires, 2025). In this work, we settle this question by formally showing that assuming independence among symbolic concepts entails that a model can never represent uncertainty over certain concept combinations. Thus, the model fails to be aware of reasoning shortcuts, i.e., the pathological behaviour of NeSy predictors that predict correct downstream tasks but for the wrong reasons.
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。