Paper recorded by Signals 4 on 2026-10-16 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-16 on arXiv · recorded by Signals 4 on 2026-10-19
Category: cs.CL · 自然语言处理 · first seen 2026-10-19
Dense assistance methods such as speculative decoding repeatedly verify draft tokens with a target model, keeping target computation coupled to generation. We study sparse collaborative decoding, where a draft model generates most tokens and a target model is invoked only for short corrective segments. The key problem is deciding when to call the target. We show that local uncertainty is a weak tr