語言模型的認知地圖：通過口語表示世界模型進行最優規劃

Cognitive Map for Language Models: Optimal Planning via Verbally Representing the World Model

June 21, 2024

作者: Doyoung Kim, Jongwon Lee, Jinho Park, Minjoon Seo

cs.AI

摘要

語言模型在各種自然語言處理任務中展現出令人印象深刻的能力，但在需要多步模擬的規劃任務中表現不佳。受人類認知過程啟發，本文探討語言模型的最佳規劃能力，該模型能構建給定環境的認知地圖。我們的實驗表明，認知地圖顯著提升了在Gridworld路徑規劃任務中的最佳和可達規劃生成能力。我們觀察到我們的方法展示了兩個與人類認知相似的關鍵特徵：將其規劃能力泛化到外推環境以及在有限訓練數據下快速適應。我們希望我們在Gridworld任務中的研究結果能夠深入了解在語言模型中建模人類認知過程，潛在地促成開發更先進和更強大的系統，更好地模擬人類認知。

English

Language models have demonstrated impressive capabilities across various natural language processing tasks, yet they struggle with planning tasks requiring multi-step simulations. Inspired by human cognitive processes, this paper investigates the optimal planning power of language models that can construct a cognitive map of a given environment. Our experiments demonstrate that cognitive map significantly enhances the performance of both optimal and reachable planning generation ability in the Gridworld path planning task. We observe that our method showcases two key characteristics similar to human cognition: generalization of its planning ability to extrapolated environments and rapid adaptation with limited training data. We hope our findings in the Gridworld task provide insights into modeling human cognitive processes in language models, potentially leading to the development of more advanced and robust systems that better resemble human cognition.