Human beings are social creatures. We routinely reason about other agents, and a crucial component of this social reasoning is inferring people's goals as we learn about their actions. In many settings, we can perform intuitive but reliable goal inference from language descriptions of agents, actions, and the background environments. In this paper, we study this process of language driving and influencing social reasoning in a probabilistic goal inference domain. We propose a neuro-symbolic model that carries out goal inference from linguistic inputs of agent scenarios. The "neuro" part is a large language model (LLM) that translates language descriptions to code representations, and the "symbolic" part is a Bayesian inverse planning engine. To test our model, we design and run a human experiment on a linguistic goal inference task. Our model closely matches human response patterns and better predicts human judgements than using an LLM alone.

翻译：人类是社会性生物。我们通常会对他人的行为进行推理，而这一社会推理的关键组成部分是在了解他人行为时推断其目标。在许多情境中，我们能够通过语言描述——关于行为主体、行动及其背景环境——进行直观且可靠的目标推断。本文在概率性目标推断领域中，研究语言驱动并影响社会推理的这一过程。我们提出一种神经符号模型，能够从行为场景的语言输入中执行目标推断。其中“神经”部分是一个大型语言模型（LLM），负责将语言描述转换为代码表示；“符号”部分则是一个贝叶斯逆向规划引擎。为验证该模型，我们设计并开展了一项针对语言目标推断任务的人类实验。实验结果表明，我们的模型与人类响应模式高度吻合，且在预测人类判断方面优于单独使用LLM的方法。