Method Drift›Speculative decoding
Superseded baseline#116 of 151 most-superseded
LLM-as-a-judge for sequence-level verification
Speculative decoding
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites LLM-as-a-judge for sequence-level verification as a baseline.
“However, they mainly rely on LLM-as-a-judge evaluations, which are prone to inaccuracies and bias, as prior studies have shown that LLM-as-a-judge can be biased and unreliable~gu2024survey,li2025evaluating,thakur2024judging.”
— Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.