从测量到专业知识：面向对话式AI智能体中基于上下文共情的共情专家适配器
From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents
AI总结：
本研究提出一个开发和评估特定上下文共情大语言模型的框架，通过合成对话生成管道训练共情专家适配器，使模型能根据任务调整共情水平，显著缩小了感知与期望共情间的差距，并在长对话中保持共情模式。
摘要：
共情是对话式AI中培养积极用户体验的关键因素。尽管模型能够表现出共情，但这种共情通常是泛化的，而非针对特定任务和上下文量身定制的。在本研究中，我们引入了一个新颖的框架，用于开发和评估特定上下文的共情大语言模型（LLMs）。我们首先分析了一个真实世界的对话数据集，包含跨8个任务的672轮多轮对话，揭示了对话前后的预期共情与体验共情之间的显著差异。为了帮助最小化这一差距，我们开发了一个合成多轮对话生成管道，并根据更贴近用户期望的上下文，将响应引导至我们定义的共情模式。随后，我们训练了用于特定上下文共情的共情专家适配器，这些适配器能够根据识别出的任务在不同共情水平上进行专门化。我们的实证结果表明，感知共情与期望共情之间的差距显著减少了72.66%，且如我们的指标和奖励模型所测量，得分平均提高了2.43倍。此外，我们训练的共情专家适配器在保持整个对话轮次中的共情模式方面表现出卓越的有效性，优于系统提示，后者在对话变长时往往会急剧减弱影响力。
英文摘要：
Empathy is a critical factor in fostering positive user experiences in conversational AI. While models can display empathy, it is often generic rather than tailored to specific tasks and contexts. In this work, we introduce a novel framework for developing and evaluating context-specific empathetic large language models (LLMs). We first analyze a real-world conversational dataset consisting of 672 multi-turn conversations across 8 tasks, revealing significant differences in terms of expected and experienced empathy before and after the conversations, respectively. To help minimize this gap, we develop a synthetic multi-turn conversational generation pipeline and steer responses toward our defined empathy patterns based on the context that more closely matches users' expectations. We then train empathetic expert adapters for context-specific empathy that specialize in varying empathy levels based on the recognized task. Our empirical results demonstrate a significant gap reduction of 72.66% between perceived and desired empathy with scores increasing by an average factor of 2.43 as measured by our metrics and reward models. Additionally, our trained empathetic expert adapters demonstrate superior effectiveness in preserving empathy patterns throughout conversation turns, outperforming system prompts, which tend to dramatically diminish in impact as conversations lengthen.
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。
