חזרה על האימות המפורק של האימות האבדני: מנגנונים, תמורות וסוגיות כשל

תקציר מקורי באנגליתarXiv:2607.26627v2 Announce Type: replace Abstract: Speculative Decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose tokens that are subsequently verified in parallel by a larger target model. Recent approaches introduce lossy verification schemes to further improve efficiency by relaxing strict distributional matching. Yet such relaxation silently rewrites the decoding distribution, and the resulting acceleration can come at the cost of unstable, sometimes severely degraded generation quality. In this work, we present a principled analysis of the distributions induced by lossy verification methods. We show that many seemingly distinct approaches differ only superficially and can be unified into two categories: truncation-based verificat