情感流动语言模型用于情感支持对话
Affective Flow Language Model for Emotional Support Conversation
AI总结：
本文提出AFlow模型，通过建模多轮对话中的连续情感流动，提供细粒度监督以提升情感支持对话中的策略一致性和共情响应质量。
摘要：
大型语言模型（LLMs）已被广泛应用于情感支持对话（ESC）。然而，复杂的多轮支持仍具挑战性，因为现有对齐方案依赖稀疏结果级信号，限制了中间策略决策的监督。为此，本文提出情感流动语言模型用于情感支持对话（AFlow），该框架通过建模多轮轨迹中的连续情感流动，对对话前缀提供细粒度监督。AFlow可以估计搜索轨迹中的中间效用，并学习偏好一致的策略转换。为提高策略一致性和共情响应质量，提出子路径级流动平衡目标，将偏好信号传播到中间状态。实验结果表明，在多样情感上下文中，AFlow在竞争性基线上的表现一致且显著。值得注意的是，AFlow使用紧凑的开源主干，在主要ESC指标上优于专有LLM如GPT-4o和Claude-3.5。我们的代码可在https://github.com/chz2025/AffectiveFlow获取。
英文摘要：
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 introduces Affective Flow Preference Optimization (AFPO), which uses a flow-balance objective defined over dialogue subpaths to propagate downstream preference signals to intermediate states and learn strategy transitions consistent with support outcomes over the full dialogue. AFlow introduces flow-balance learning into multi-turn affective interaction, providing a process-based approach to dynamic affect modeling and continuous strategy optimization. Experiments on ExTES and ESConv show consistent improvements in strategy alignment, response diversity, and generation quality across different model environments and evaluation settings. Our code is available at https://github.com/chz2025/AffectiveFlow.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
