示範：利用細粒度元素建模重新構思對話互動

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling

December 6, 2024

作者: Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li

cs.AI

摘要

大型語言模型（LLMs）已使對話成為人機互動的核心模式之一，導致大量對話日誌的累積，並增加了對對話生成的需求。對話生命週期從序幕、通話到結語，包含各種元素。儘管存在許多與對話相關的研究，但缺乏包含全面對話元素的基準，阻礙了精確建模和系統評估。為彌補這一差距，我們引入了一項創新的研究任務——對話元素建模，包括元素意識和對話代理互動，並提出了一個新穎的基準 DEMO，旨在進行全面的對話建模和評估。受到模仿學習的啟發，我們進一步建立了一個代理，具有模擬對話元素的熟練能力，基於 DEMO 基準。廣泛的實驗表明，現有的 LLMs 仍具有相當大的增強潛力，而我們的 DEMO 代理在領域內和領域外任務中均表現優異。

English

Large language models (LLMs) have made dialogue one of the central modes of human-machine interaction, leading to the accumulation of vast amounts of conversation logs and increasing demand for dialogue generation. A conversational life-cycle spans from the Prelude through the Interlocution to the Epilogue, encompassing various elements. Despite the existence of numerous dialogue-related studies, there is a lack of benchmarks that encompass comprehensive dialogue elements, hindering precise modeling and systematic evaluation. To bridge this gap, we introduce an innovative research task Dialogue Element MOdeling, including Element Awareness and Dialogue Agent Interaction, and propose a novel benchmark, DEMO, designed for a comprehensive dialogue modeling and assessment. Inspired by imitation learning, we further build the agent which possesses the adept ability to model dialogue elements based on the DEMO benchmark. Extensive experiments indicate that existing LLMs still exhibit considerable potential for enhancement, and our DEMO agent has superior performance in both in-domain and out-of-domain tasks.