הפרדת קבלת החלטות ממשמעות: גישה נפרדת לנתונים למכוניות מצב סופי-מצביות לשיחה דו-כיוונית

תקציר מקורי באנגליתarXiv:2609.03321v1 Announce Type: new Abstract: The Neural Finite State Machine (NFSM) framework offers a pragmatic path to full-duplex dialogue by serializing turn-taking control and response generation onto a single causal tape under the standard next-token prediction objective, thereby preserving semantic prowess at a low fine-tuning cost. However, its reliance on synthetic text data fundamentally limits turn-taking naturalness, as Large Language Models (LLMs) cannot faithfully simulate the fine-grained acoustic temporal dynamics of real human dialogues. In this work, we propose a decoupled data approach that learns turn-taking from real Human-Human (HH) spoken dialogues while shaping semantic behavior through configurable Human-Agent (HA) text dialogues. To operationalize this approach