Stephanie:用于在社交对话中模拟人类交互的分步对话机制
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
AI总结:
针对现有对话系统单步范式缺乏自然交互深度的问题,研究提出分步对话范式Stephanie,通过双重学习与拆分后编辑生成数据集微调大模型,经评估效果优于传统单步范式,并将开源相关资源。
摘要:
在快速发展的自然语言处理领域,对话系统主要采用单步对话范式。该范式虽高效,却缺乏人类交互的深度与流畅性,表现不够自然。我们提出一种新颖的分步对话范式Stephanie,旨在模拟人类对话的持续动态特性。通过采用双重学习策略和进一步拆分的后编辑方法,我们生成并利用高质量的分步对话数据集来微调现有大语言模型,使其能够执行分步对话。我们对Stephanie进行了全面介绍,并开展了定制化的自动评估与人工评估,以衡量其相较于传统单步对话范式的有效性。我们将发布代码、Stephanie数据集和Stephanie大语言模型,以推动聊天机器人时代的未来发展。
英文摘要:
In the rapidly evolving field of natural language processing, dialogue systems primarily employ a single-step dialogue paradigm. Although this paradigm is efficient, it lacks the depth and fluidity of human interactions and does not appear natural. We introduce a novel \textbf{Step}-by-Step Dialogue Paradigm (Stephanie), designed to mimic the ongoing dynamic nature of human conversations. By employing a dual learning strategy and a further-split post-editing method, we generated and utilized a high-quality step-by-step dialogue dataset to fine-tune existing large language models, enabling them to perform step-by-step dialogues. We thoroughly present Stephanie. Tailored automatic and human evaluations are conducted to assess its effectiveness compared to the traditional single-step dialogue paradigm. We will release code, Stephanie datasets, and Stephanie LLMs to facilitate the future of chatbot eras.
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。