TALES

该数据集是一个包含了多种由人工智能合成以及人类编写的文本冒险游戏，旨在对各种推理能力进行挑战和评估。该数据集不仅涵盖了需要不同推理技能的游戏环境，还特别强调了通过定制化的评分规则来评估大型语言模型（LLMs）的表现。规模上，该数据集包含了多个游戏环境，其评分规则从0到100不等。任务目标是评估大型语言模型在文本冒险游戏中展现的推理能力。

This dataset consists of a diverse set of text adventure games generated by artificial intelligence and written by humans, aiming to challenge and evaluate various reasoning abilities. The dataset not only covers game environments that require distinct reasoning skills, but also places special emphasis on evaluating the performance of Large Language Models (LLMs) through customized scoring rules. In terms of scale, the dataset includes multiple game environments, with their scoring ranges varying from 0 to 100. The task objective is to assess the reasoning capabilities exhibited by large language models during their gameplay in text adventure games.