Unverified50% confidenceFactExact time
SHAP and LIME are both post-hoc explanation frameworks that do not modify the model itself, but instead generate explanations after predictions are made.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSHAP的核心思想是将每个特征对模型预测的贡献量化，使得所有特征贡献之和等于模型预测值与基线值的差72% similarUnverifiedLIME explains individual predictions by generating a perturbed dataset around the input sample to train a local linear approximation model, while SHAP provides feature attribution based on game-theoretic Shapley values; both are model-agnostic techniques.70% 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69% similarUnverifiedSHAP (SHapley Additive exPlanations) is a mainstream machine learning model explanation framework whose theoretical basis derives from Shapley values in game theory.69% similarVerifiedWith LoRA, the weights can be merged back into the original model at inference time, introducing no additional latency69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984704API
curl https://kongchang.com/api/v1/knowledge/claims/984704MCP
get_claim(id=984704)