BOHM extracts multi-resolution attribution trees from existing routing weights in hierarchical AI systems, providing zero-cost explanations that correlate with SHAP when routing is near-optimal.
GShard: Scaling giant models with conditional computation and automatic sharding
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.AI 3years
2026 3representative citing papers
Routing topology in sparse Mixture-of-Experts models does not determine asymptotic language modeling perplexity; multiple variants including cosine-similarity routing achieve statistically equivalent performance.
Cosine-similarity routing in low-dimensional space makes MoE experts monosemantic by construction and enables direct causal control via centroid interventions.
citing papers explorer
-
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
BOHM extracts multi-resolution attribution trees from existing routing weights in hierarchical AI systems, providing zero-cost explanations that correlate with SHAP when routing is near-optimal.
-
Equifinality in Mixture of Experts: Routing Topology Does Not Determine Language Modeling Quality
Routing topology in sparse Mixture-of-Experts models does not determine asymptotic language modeling perplexity; multiple variants including cosine-similarity routing achieve statistically equivalent performance.
-
Geometric Routing Enables Causal Expert Control in Mixture of Experts
Cosine-similarity routing in low-dimensional space makes MoE experts monosemantic by construction and enables direct causal control via centroid interventions.