Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.
Analytical estimates of limited sampling biases in different information measures.Network: Computation in neural systems, 7(1):87
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.