从词模型到世界模型：从自然语言翻译到思维的概率语言

From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought

June 22, 2023

作者: Lionel Wong, Gabriel Grand, Alexander K. Lew, Noah D. Goodman, Vikash K. Mansinghka, Jacob Andreas, Joshua B. Tenenbaum

cs.AI

摘要

语言如何影响我们的下游思维？特别是，人类如何从语言中获得意义，以及我们如何利用语言意义理论来构建更类人思维的机器？在本文中，我们提出了理性意义构建，这是一个结合了神经语言模型和概率推理模型的计算框架，用于受语言启发的思维。我们将语言意义框架化为一种从自然语言到概率思维语言（PLoT）的上下文敏感映射，PLoT是一种用于概率生成世界建模的通用符号基质。我们的架构整合了两种强大的计算工具，这两者以前从未结合过：我们使用概率程序来建模思维，这是一种灵活的常识推理表达方式；我们使用大型语言模型（LLMs）来建模意义构建，支持从自然语言话语到概率编程语言代码表达的广泛翻译。我们通过涵盖认知科学的四个核心领域的示例展示了我们的框架：概率推理、逻辑和关系推理、视觉和物理推理，以及关于代理人及其计划的社会推理。在每个领域中，我们展示了LLMs可以生成捕捉到语用适当的语言意义的上下文敏感翻译，而使用生成的程序进行贝叶斯推理则支持连贯且强大的常识推理。我们扩展了我们的框架，以整合认知动机符号模块，提供一个从语言到统一常识思维接口。最后，我们探讨了语言如何驱动世界模型本身的构建。

English

How does language inform our downstream thinking? In particular, how do humans make meaning from language -- and how can we leverage a theory of linguistic meaning to build machines that think in more human-like ways? In this paper, we propose rational meaning construction, a computational framework for language-informed thinking that combines neural models of language with probabilistic models for rational inference. We frame linguistic meaning as a context-sensitive mapping from natural language into a probabilistic language of thought (PLoT) -- a general-purpose symbolic substrate for probabilistic, generative world modeling. Our architecture integrates two powerful computational tools that have not previously come together: we model thinking with probabilistic programs, an expressive representation for flexible commonsense reasoning; and we model meaning construction with large language models (LLMs), which support broad-coverage translation from natural language utterances to code expressions in a probabilistic programming language. We illustrate our framework in action through examples covering four core domains from cognitive science: probabilistic reasoning, logical and relational reasoning, visual and physical reasoning, and social reasoning about agents and their plans. In each, we show that LLMs can generate context-sensitive translations that capture pragmatically-appropriate linguistic meanings, while Bayesian inference with the generated programs supports coherent and robust commonsense reasoning. We extend our framework to integrate cognitively-motivated symbolic modules to provide a unified commonsense thinking interface from language. Finally, we explore how language can drive the construction of world models themselves.