STICKERCONV：从零开始生成多模态共情回复
STICKERCONV: Generating Multimodal Empathetic Responses from Scratch
AI总结：
针对表情包在共情对话研究中缺乏数据集的问题，提出Agent4SC模拟人类行为并构建STICKERCONV基准，同时开发PEGS框架生成多模态共情回复，有效提升了回复的情境相关性与情感共鸣。
摘要：
表情包虽因在在线互动中增强共情交流而广受认可，但在当前的共情对话研究中仍探讨不足，这主要由于缺乏全面的数据集所带来的挑战。本文介绍了STICKERCONV的智能体（Agent4SC），它利用协作智能体交互来真实模拟人类使用表情包的行为，从而增强多模态共情交流。在此基础之上，我们开发了多模态共情对话数据集STICKERCONV，包含12.9K个对话会话、5.8K个独特表情包和2K个多样化对话场景。该数据集作为多模态共情生成的基准。为进一步推进，我们提出了PErceive and Generate Stickers（PEGS），一个多模态共情回复生成框架，并辅以一套基于LLM的全面共情评估指标。我们的实验证明了PEGS在生成上下文相关且情感共鸣的多模态共情回复方面的有效性，有助于推进更细致、更引人入胜的共情对话系统。
英文摘要：
Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets. In this paper, we introduce the Agent for STICKERCONV (Agent4SC), which uses collaborative agent interactions to realistically simulate human behavior with sticker usage, thereby enhancing multimodal empathetic communication. Building on this foundation, we develop a multimodal empathetic dialogue dataset, STICKERCONV, comprising 12.9K dialogue sessions, 5.8K unique stickers, and 2K diverse conversational scenarios. This dataset serves as a benchmark for multimodal empathetic generation. To advance further, we propose PErceive and Generate Stickers (PEGS), a multimodal empathetic response generation framework, complemented by a comprehensive set of empathy evaluation metrics based on LLM. Our experiments demonstrate PEGS's effectiveness in generating contextually relevant and emotionally resonant multimodal empathetic responses, contributing to the advancement of more nuanced and engaging empathetic dialogue systems.
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。
