Unverified50% confidenceFactExact time
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、LIME
1
Sources
50%
Confidence
Long-term
Relevance
8/9/2026
First Seen
Sources
Related Claims
Unverified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71% similarUnverifiedLIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations) are the primary tools for providing post-hoc explanations for complex black-box models.69% similarUnverified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68% similarUnverifiedContent with clear structure and unambiguous semantics is easier for LLMs to parse and can effectively reduce the risk of the model generating hallucinations.64% 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61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/719119API
curl https://kongchang.com/api/v1/knowledge/claims/719119MCP
get_claim(id=719119)