通过连续情绪流建模，让对话模型更懂中途的情感支持策略。
Affective Flow Language Model for Emotional Support Conversation
- 用连续情绪流监督对话前缀，细化中间决策
- 小模型超越GPT-4o和Claude-3.5在情感支持任务上
- 适合需要精准共情与策略连贯性的对话系统研发
大语言模型在情感支持对话（ESC）中应用广泛，但复杂的多轮支持仍具挑战。现有对齐机制依赖稀疏的结局级信号，难以有效指导中间策略选择。为此，本文提出情感流语言模型（AFlow），通过建模多轮轨迹中的连续情绪流，在对话前缀层面引入细粒度监督。AFlow可估计搜索轨迹中各阶段的中间效用，并学习偏好一致的策略转移。为提升策略连贯性与共情响应质量，提出子路径级流平衡目标，将偏好信号传播至中间状态。实验表明，AFlow在多种情绪情境下均显著优于主流基线。值得注意的是，采用轻量开源骨干模型的AFlow在主要ESC指标上超越GPT-4o与Claude-3.5等专有大模型。代码已开源。
原文摘要 · Abstract (English)
Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains challenging.This is because existing alignment schemes rely on sparse outcome-level signals, thus offering limited supervision for intermediate strategy decisions. To fill this gap, this paper proposes affective flow language model for emotional support conversation (AFlow), a framework that introduces fine-grained supervision on dialogue prefixes by modeling a continuous affective flow along multi-turn trajectories. AFlow can estimate intermediate utility over searched trajectories and learn preference-consistent strategy transitions. To improve strategy coherence and empathetic response quality, a subpath-level flow-balance objective is presented to propagate preference signals to intermediate states. Experiment results show consistent and significant improvements over competitive baselines in diverse emotional contexts. Remarkably, AFlow with a compact open-source backbone outperforms proprietary LMMs such as GPT-4o and Claude-3.5 on major ESC metrics. Our code is available at https://github.com/chz2025/AffectiveFlow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。