מודל שפה Affective Flow לשיחות תמיכה רגשית

תקציר מקורי באנגליתarXiv:2602.08826v3 Announce Type: replace Abstract: Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level or outcomes at the dialogue level, providing limited supervision for sequential strategy decisions in multi-turn interactions. This raises a key question: how can detailed process signals be derived from overall dialogue outcomes to guide the gradual adaptation of support strategies? We propose the Affective Flow Language Model (AFlow), which models multi-turn emotional support as an affective utility flow evolving along dialogue trajectories. AFlow searches diverse support trajectories and estimates the utility of intermediate dialogue states and candidate strategies. It further