多视角指称交流中的语言接地
Grounding Language in Multi-Perspective Referential Communication
AI总结：
该研究提出多智能体具身环境下的多视角指称交流任务与含2970条样本的数据集，发现现有模型性能弱于人类双人组合，经交流成功信号训练的开源说话者模型成功率达69.3%，超最强专有模型。
摘要：
我们提出了一项面向多智能体具身环境中指代表达生成与理解的任务及对应数据集。该任务中，共享场景内的两个智能体需考虑彼此可能存在差异的视觉视角，以生成并理解指向场景内物体及其空间关系的指称表述。我们收集了包含2970条人工撰写指代表达的数据集，每条均配有人类理解判断结果；评估了自动模型分别以说话者、听者身份与人类搭档配对的表现，发现模型在指称生成与理解两方面的性能均落后于双人人类搭档组合。最后，我们通过实验训练了一个开源权重说话者模型，训练时引入与听者配对的交流成功信号，最终交流成功率从58.9%提升至69.3%，甚至超过了性能最强的专有模型。
英文摘要：
We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments. In this task, two agents in a shared scene must take into account one another's visual perspective, which may be different from their own, to both produce and understand references to objects in a scene and the spatial relations between them. We collect a dataset of 2,970 human-written referring expressions, each paired with human comprehension judgments, and evaluate the performance of automated models as speakers and listeners paired with human partners, finding that model performance in both reference generation and comprehension lags behind that of pairs of human agents. Finally, we experiment training an open-weight speaker model with evidence of communicative success when paired with a listener, resulting in an improvement from 58.9 to 69.3% in communicative success and even outperforming the strongest proprietary model.
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。
