Proceedings

Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection (Extended Abstract)

Wen-Chao Hu, Wang-Zhou Dai, Yuan Jiang, Zhi-Hua Zhou

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 10896-10900.

https://doi.org/10.24963/ijcai.2025/1212

Keywords

  • Sister Conferences Best Papers: Constraint Satisfaction and Optimization
  • Sister Conferences Best Papers: Machine Learning

Abstract

Neuro-Symbolic (NeSy) AI could be regarded as an analogy to human dual-process cognition, modeling the intuitive System 1 with neural networks and the algorithmic System 2 with symbolic reasoning. However, for complex learning targets, NeSy systems often generate outputs inconsistent with domain knowledge. Inspired by the human Cognitive Reflection, which promptly detects errors in our intuitive response and revises them by invoking the System 2 reasoning, we propose to improve NeSy systems by introducing Abductive Reflection (ABL-Refl) based on the Abductive Learning (ABL) framework. ABL-Refl leverages domain knowledge to abduce a reflection vector during training, which can then flag potential errors in the neural network outputs and invoke abduction to rectify them and generate consistent outputs during inference. Experiments show that ABL-Refl outperforms state-of-the-art NeSy methods, achieving excellent accuracy with fewer training resources and enhanced efficiency.

Wen-Chao Hu, Wang-Zhou Dai, Yuan Jiang, and Zhi-Hua Zhou. 2025. Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection (Extended Abstract). In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10896–10900. https://doi.org/10.24963/ijcai.2025/1212
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards