Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions

Autor:	Tsai, Chen Feng, Zhou, Xiaochen, Liu, Sierra S., Li, Jing, Yu, Mo, Mei, Hongyuan
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated their remarkable abilities of communicating with human users. In this technical report, we take an initiative to investigate their capacities of playing text games, in which a player has to understand the environment and respond to situations by having dialogues with the game world. Our experiments show that ChatGPT performs competitively compared to all the existing systems but still exhibits a low level of intelligence. Precisely, ChatGPT can not construct the world model by playing the game or even reading the game manual; it may fail to leverage the world knowledge that it already has; it cannot infer the goal of each step as the game progresses. Our results open up new research questions at the intersection of artificial intelligence, machine learning, and natural language processing.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.02868 Zobrazit plný text záznamu View this record from Arxiv