面向对话任务助手的多特质用户模拟与自适应解码
Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
AI总结：
针对对话任务助手中多样用户特质难以模拟的问题，提出 mTAD，在解码时从特质专属 LM 采样以生成多画像对话，并通过 CTA 真实对话实验验证其有效性与灵活性。
摘要：
对话系统必须对自然展现出多样对话特质的用户交互具有鲁棒性。连贯且高效地捕捉并模拟这些多样特质是一项复杂挑战。本文提出 Multi-Trait Adaptive Decoding（mTAD，多特质自适应解码），该方法通过从多个特质专属语言模型（LM）中采样，在解码阶段生成多样化用户画像。mTAD 为用户模拟提供了一种自适应且可扩展的方法，无需额外微调即可创建多个用户画像。通过分析来自 Conversational Task Assistant（CTA，对话任务助手）领域的真实对话，我们识别出关键对话特质，并开发了一个框架来生成增强对话多样性的画像感知对话。实验结果验证了本方法利用专门化 LM 建模单一特质的有效性，这些模型即使在域外任务中也能捕捉较少见的模式。此外，结果表明 mTAD 是一个用于组合多样化用户模拟器的鲁棒且灵活的框架。
英文摘要：
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.
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。
