Unverified50% confidenceFactExact time
SHAP values and LIME are commonly used local interpretability methods capable of quantifying each feature's contribution to a single decision.
1
Sources
50%
Confidence
Long-term
Relevance
8/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSHAP值通过博弈论中的沙普利值方法量化每个特征对单一预测结果的贡献度，LIME通过在预测点附近构建局部线性近似模型解释个案决策79% similarVerifiedSHAP基于博弈论中的Shapley值，能够量化每个特征对最终预测结果的贡献度，是目前工业界应用最广泛的解释性工具之一76% similarUnverifiedSHAP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74% similarUnverifiedSHAP用于特征归因（解释每个特征对预测的贡献度），DiCE用于生成多样化的反事实样本，二者互补71% similarUnverified多模态模型在'何时使用何种能力'的精细判断上容易出现越界行为67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823685API
curl https://kongchang.com/api/v1/knowledge/claims/823685MCP
get_claim(id=823685)