Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in dialogues, including expressing empathy and offering emotional support. Despite having access to commonsense knowledge to better understand the psychological aspects and causality of dialogue context, even these powerful LLMs struggle to achieve the goals of empathy and emotional support. As current approaches do not adequately anticipate dialogue future, they may mislead language models to ignore complex dialogue goals of empathy and emotional support, resulting in unsupportive responses lacking empathy. To address this issue, we present an innovative framework named Sensible Empathetic Dialogue Generation with Visionary Commonsense Knowledge (Sibyl). Designed to concentrate on the imminent dialogue future, this paradigm directs LLMs toward the implicit requirements of the conversation, aiming to provide more sensible responses. Experimental results demonstrate that incorporating our paradigm for acquiring commonsense knowledge into LLMs comprehensively enhances the quality of their responses.

翻译：近年来，基于大语言模型构建能够模拟人类对话特质（包括表达共情和提供情感支持）的聊天机器人引起了广泛关注。尽管这些强大的大语言模型能够利用常识知识来更好地理解对话语境的心理层面和因果关系，它们仍难以实现共情与情感支持的目标。由于现有方法未能充分预测对话的未来走向，可能导致语言模型忽视共情与情感支持这一复杂对话目标，从而生成缺乏共情、无支持性的回应。为解决这一问题，我们提出了一种创新框架——基于前瞻性常识知识的理性共情对话生成（Sibyl）。该范式旨在聚焦即将发生的对话未来，引导大语言模型关注对话中的隐含需求，以提供更具理性的回应。实验结果表明，将我们提出的常识知识获取范式融入大语言模型，能够全面提升其生成回复的质量。