Speculative decoding
token-level speculative decoding
Superseded baseline#145 of 151 most-superseded
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites token-level speculative decoding as a baseline.
However, existing work either in improving drafting and verification remains token-level, overlooking semantic equivalence between drafts and target outputs, as discussed in Section~sec:intro, which still potentially reject good candidates and leads to low acceptance rate.
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.