发表机构
Honda Research Institute Japan; University of Cambridge（本田研究所日本分部; 剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对社会机器人选择基础模型的难题，本文提出三层评估漏斗范式，梳理五个评估维度的适用评估方法，呼吁社区共建评估框架。
AI 中文摘要
试图基于基础模型构建社会机器人应用的研究人员面临一个难题：我们应如何选择模型？公开排行榜几乎无法提供指导，因为实时具身社会交互的需求大多不在其关注范围内；而直接评估在大规模场景下不具可行性，每项具身研究都需要稀缺的参与者、机器人及实验人员时间。本文确定了社会机器人基础模型的五个评估维度：（i）对话能力，（ii）用户安全性，（iii）具身特性，（iv）目标场景有效性，（v）受众适配性。为降低模型选择成本并提供更充分的信息，我们提出了三层评估漏斗范式：先用通用指标筛选，再扩展至模拟交互，最后以成本更高的机器人特定评估收尾。我们将五个维度映射到三个层级，梳理了适用评估方法的存在情况与缺失之处，并以行动呼吁作结：让我们作为一个社区共同构建该评估框架。
英文摘要
Researchers who seek to build social robot applications on foundation models are faced with a difficult question: how should we pick a model? Public leaderboards offer little guidance: the demands of real-time, embodied social interaction lie largely outside their focus. And direct evaluation is impractical at scale: each embodied study requires scarce participant, robot, and experimenter time. In this paper, we identify five evaluation dimensions for foundation models in social robots: (i) conversational competence, (ii) user safety, (iii) embodied character, (iv) target scene effectiveness, and (v) audience appropriateness. To make model selection cheaper and better informed, we propose a three-tiered evaluation funnel paradigm that first filters with general metrics, then extends to simulated interactions, and terminates in more expensive, robot-specific evaluation. We map all five dimensions across all three tiers, chart where applicable evaluation methods exist and are missing, and close with a call to action: let's build the evaluation framework together as a community.
Comments5 pages, 1 figure, 1 table. Accepted at the FoRMA workshop (Foundation Models in the RO-MAN Age: Responsible Development for Social Robotics) at IEEE RO-MAN 2026, Kitakyushu, Japan. Workshop homepage: https://sites.google.com/cam.ac.uk/forma/
