对话式朝向推理：基于多模态思维链的自我中心到异我中心导航
Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thought
AI总结：
本文提出对话式朝向推理基准COR和多模态思维链框架MCoT，通过三步结构化推理将自我中心表述转换为绝对朝向，在繁体中文导航中实现高准确率与鲁棒性。
摘要：
对话智能体必须将自我中心表述（例如“在我的右边”）转换为异我中心朝向（北/东/南/西）。这一挑战在GPS信号弱且缺乏详细地图的室内或复杂设施中尤为关键。尽管思维链（CoT）提示已在语言和视觉任务中推进了推理能力，但其在多模态空间朝向中的应用仍未得到充分探索。我们提出了对话式朝向推理（COR），这是一个新的基准，专为从真实世界环境投射而来的繁体中文对话导航而设计，用于解决非英语和ASR转录场景下的自我中心到异我中心推理问题。我们提出了一个多模态思维链（MCoT）框架，该框架通过结构化的三步推理过程将ASR转录语音与地标坐标整合起来：（1）提取空间关系，（2）将坐标映射到绝对方向，（3）推断用户朝向。我们采用课程学习策略，在Taiwan-LLM-13B-v2.0-Chat上逐步构建这些能力，该模型是一个具有代表性的中等规模模型，适用于资源受限环境。实验表明，MCoT在干净转录上实现了100%的朝向准确率，在ASR转录上实现了98.1%的准确率，显著优于单模态和非结构化基线。此外，MCoT在嘈杂对话条件下表现出鲁棒性，包括ASR识别错误和多语言语码转换。该模型在跨领域评估中也保持了高准确率，并对语言变异、领域偏移和指代歧义具有韧性。这些发现凸显了结构化MCoT空间推理作为通向可解释且资源高效的具身导航路径的潜力。
英文摘要：
Conversational agents must translate egocentric utterances (e.g., "on my right") into allocentric orientations (N/E/S/W). This challenge is particularly critical in indoor or complex facilities where GPS signals are weak and detailed maps are unavailable. While chain-of-thought (CoT) prompting has advanced reasoning in language and vision tasks, its application to multimodal spatial orientation remains underexplored. We introduce Conversational Orientation Reasoning (COR), a new benchmark designed for Traditional Chinese conversational navigation projected from real-world environments, addressing egocentric-to-allocentric reasoning in non-English and ASR-transcribed scenarios. We propose a multimodal chain-of-thought (MCoT) framework, which integrates ASR-transcribed speech with landmark coordinates through a structured three-step reasoning process: (1) extracting spatial relations, (2) mapping coordinates to absolute directions, and (3) inferring user orientation. A curriculum learning strategy progressively builds these capabilities on Taiwan-LLM-13B-v2.0-Chat, a mid-sized model representative of resource-constrained settings. Experiments show that MCoT achieves 100% orientation accuracy on clean transcripts and 98.1% with ASR transcripts, substantially outperforming unimodal and non-structured baselines. Moreover, MCoT demonstrates robustness under noisy conversational conditions, including ASR recognition errors and multilingual code-switching. The model also maintains high accuracy in cross-domain evaluation and resilience to linguistic variation, domain shift, and referential ambiguity. These findings highlight the potential of structured MCoT spatial reasoning as a path toward interpretable and resource-efficient embodied navigation.
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。
