用动态解码模拟多种用户性格，提升对话系统多样性。
Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
- 解码时从不同性格的专用语言模型中采样生成用户画像。
- 在真实对话数据上验证，能有效捕捉少见对话模式。
- 无需额外微调，适合构建多样化对话测试环境。
对话系统需应对自然对话中多样的用户行为特征。本文提出多特质自适应解码（mTAD），通过在解码阶段从多个特定性格的语言模型中采样，动态生成多样化的用户画像。该方法无需额外微调，即可高效构建多用户模拟。基于对话任务助手（CTA）领域的实际对话数据，研究识别出关键对话特质，并构建了能生成与用户画像一致的对话框架。实验表明，使用专用语言模型可有效建模单一特质，即使在跨领域任务中也能捕捉稀有对话模式。同时，mTAD展现出强鲁棒性与灵活性，适用于融合多种用户模拟器。
原文摘要 · Abstract (English)
Conversational systems must be robust to user interactions that naturally exhibit diverse conversational traits. Capturing and simulating these diverse traits coherently and efficiently presents a complex challenge. This paper introduces Multi-Trait Adaptive Decoding (mTAD), a method that generates diverse user profiles at decoding-time by sampling from various trait-specific Language Models (LMs). mTAD provides an adaptive and scalable approach to user simulation, enabling the creation of multiple user profiles without the need for additional fine-tuning. By analyzing real-world dialogues from the Conversational Task Assistant (CTA) domain, we identify key conversational traits and developed a framework to generate profile-aware dialogues that enhance conversational diversity. Experimental results validate the effectiveness of our approach in modeling single-traits using specialized LMs, which can capture less common patterns, even in out-of-domain tasks. Furthermore, the results demonstrate that mTAD is a robust and flexible framework for combining diverse user simulators.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。