CORAL (Speculative decoding): cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here. 2 paper(s) critique it, 0 beat it on benchmarks — #69 of 151 most-superseded. Sub-problem: cluster led by FR-Spec. Newer alternatives in the same sub-problem include SlimSpec, EvoSpec, MicroSpec.

Speculative decoding

CORAL

CoRAL: a Context-aware Croatian Abusive Language Dataset

Superseded baseline#69 of 151 most-superseded · first seen Nov 11, 2022

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

2 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites CORAL as a baseline.

CORAL... does not explicitly construct a context-specific active vocabulary or perform online draft-target alignment under domain shifts.

— EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter AdaptationTarget

“The latter can become a noticeable bottleneck on GPUs because it involves such operations as global ranking, partial sorting, irregular indexing and gathering a context-dependent subset of weights, which are less efficient than dense matrix multiplication.”

— SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.