Unverified50% confidenceFactExact time
机械可解释性区别于传统可解释性（如LIME、SHAP等事后近似解释方法），追求对模型内部计算结构的精确、机械式理解
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
因果理论破解大模型黑箱：机械可解释性的新范式
Related Claims
Unverified内在可解释性指模型结构本身的透明性，事后可解释性则是对不透明模型施加外部解释技术如SHAP、LIME68% similarUnverifiedAn ontology is a formal, structured representation of knowledge in a specific domain that explicitly defines concepts, attributes, and relationships between concepts, enabling machines to perform logical reasoning.68% similarUnverified机制可解释性致力于逆向工程神经网络内部的算法结构，与传统黑盒解释方法（如LIME、SHAP）不同65% similarUnverified可说明性（Explainability）催生了LIME、SHAP等事后归因方法，面向外部用户回答为什么模型给出该输出65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/509889API
curl https://kongchang.com/api/v1/knowledge/claims/509889MCP
get_claim(id=509889)