Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations

TL;DR

Stephanie introduces a step-by-step dialogue paradigm that enhances the naturalness and depth of conversational AI by mimicking human interaction dynamics through a novel dual learning and post-editing approach.

Contribution

The paper presents a new step-by-step dialogue framework, a high-quality dataset, and fine-tuning methods to improve the naturalness of AI conversations.

Findings

Stephanie outperforms traditional single-step dialogue models in naturalness.

Automatic and human evaluations validate the effectiveness of Stephanie.

The approach enables more fluid and human-like interactions in chatbots.

Abstract

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.