Affective Flow Language Model for Emotional Support Conversation
This work addresses the problem of providing effective emotional support in AI conversations for users needing multi-turn interactions, representing a novel method for a known bottleneck.
The paper tackles the challenge of complex multi-turn emotional support conversation by proposing AFlow, a framework that introduces fine-grained supervision on dialogue prefixes to model affective flow, resulting in consistent and significant improvements over competitive baselines, including outperforming proprietary models like GPT-4o and Claude-3.5 on major ESC metrics.
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/chzou25-lgtm/AffectiveFlow.