LoCar: 通过细粒度社会语言学控制评估车载助手的本地化
LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control
AI总结：
本文提出了一种新的车载助手评估框架，专注于韩语本地化，揭示了当前LLM在细粒度韩语敬语控制方面的不稳定性以及策略性对话指标上的表现不足，强调了汽车AI需要向精确语言定制和可靠安全交互管理发展。
摘要：
尽管大型语言模型（LLMs）越来越多地集成到车载对话系统中，但由于缺乏针对实际部署需求定制的领域特定评估标准，确定最优模型仍具挑战性。在本文中，我们提出了一种新的车载助手评估框架，特别关注韩语本地化。我们的实证分析揭示了模型行为中的显著模式。首先，细粒度韩语敬语控制在当前LLM中仍然不稳定，表明在本地化设置中必须明确评估精确的语音层面实现。其次，模型在战略对话指标如澄清和主动性方面表现较弱。我们的分析表明，这源于这些任务本身的主观复杂性，其中我们的框架采取保守的评估立场以优先考虑可靠性。总体而言，我们的发现强调，汽车AI必须超越一般能力，向精确语言定制和可靠、以安全为导向的交互管理发展。
英文摘要：
While Large Language Models (LLMs) are increasingly integrated into in-vehicle conversational systems, identifying the optimal model remains challenging due to the lack of domain-specific evaluation standards tailored to real-world deployment requirements. In this paper, we propose a novel evaluation framework for in-vehicle assistants, with a particular focus on Korean-language localization. Our empirical analysis reveals notable patterns in model behavior. First, fine-grained Korean honorific control remains unstable in current LLMs, indicating that precise speech-level realization must be explicitly evaluated in localization settings. Second, models exhibit weaker performance in strategic conversational metrics like clarification and proactivity. Our analysis suggests this stems from the inherent subjective complexity of these tasks, where our framework adopts a conservative evaluation stance to prioritize reliability. Together, our findings underscore that automotive AI must move beyond general competence toward precise linguistic tailoring and reliable, safety-oriented interaction management.
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。
