Scholar Feed

Speculative decoding

DART

DART: Open-Domain Structured Data Record to Text Generation

Superseded baseline#28 of 151 most-superseded · first seen Jul 6, 2020

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 2 beat it on benchmarks

What papers say

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

Still, it relies on continuity-aware tree pruning with an external $N$-gram continuity score and a large $N$-gram trie at runtime~liu2026dart. By contrast, our proposed DDTree keeps the same one-pass DFlash drafter and constructs the tree directly from the per-position probabilities produced by that pass. This avoids auxiliary external scoring and gives an explicit surrogate objective that our best-first construction provably maximizes.
— Accelerating Speculative Decoding with Block Diffusion Draft Trees

Beaten on benchmarks

Head-to-head results where a newer method reports beating DART. Values are copied from the source paper's tables — verify against the cited paper.

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.