Unverified50% confidenceFactExact time
Exactly computing the Shapley value requires summing over 2^n subsets; for n=20 about 1 million model evaluations are needed, and for n=30 more than 1 billion, which is infeasible in practice.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSHAP精确计算需要遍历所有2^n个特征子集，当特征数超过20时精确计算已不可行，实际中采用TreeSHAP或KernelSHAP等近似算法75% similarUnverifiedThe parameter scale of large models is often expressed in abstract numbers such as hundreds of billions or trillions, lacking intuitive perception.65% similarUnverifiedThe model places n-gram lookup tables at layers 1 and 14, with 24 hashes each indexing approximately 16 million rows, totaling 196 billion parameters, exceeding one-third of the model's weights.64% similarUnverifiedThe full Neural 3 model with 121 million parameters has an actual computational load roughly equivalent to a 50-million-parameter model.64% similarUnverifiedThe GPU resources required for a single inference of a hundred-billion-parameter flagship model may be 10 to 20 times higher than those of a ten-billion-parameter model.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005573API
curl https://kongchang.com/api/v1/knowledge/claims/1005573MCP
get_claim(id=1005573)