PizzaCommonSense：学习对烹饪食谱中中间步骤的常识推理进行建模
PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes
AI总结：
本文提出烹饪食谱中间步骤常识推理语料库PizzaCommonSense，通过要求显式输入输出描述评估LLM推理能力，发现GPT-4仅获26%人类偏好。
摘要：
理解程序性文本（如烹饪食谱）对于使机器能够遵循指令并对任务进行推理至关重要，这是智能推理的一个关键方面。在烹饪中，这些指令可以解释为对食物准备过程的一系列修改。为了使模型能够有效地对烹饪食谱进行推理，它必须准确地辨别和理解食谱中中间步骤的输入和输出。我们提出了一个新的烹饪食谱语料库，其中丰富了对中间步骤的描述，这些描述说明了每个步骤的输入和输出。PizzaCommonsense 作为 LLM 推理能力的基准，因为它要求提供严格的显式输入输出描述，以证明对隐式常识知识的掌握，而这些知识不太可能被轻易记住。GPT-4 在生成内容上仅获得了 26% 的人类评估偏好，为未来的改进留下了空间。
英文摘要：
Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In cooking, these instructions can be interpreted as a series of modifications to a food preparation. For a model to effectively reason about cooking recipes, it must accurately discern and understand the inputs and outputs of intermediate steps within the recipe. We present a new corpus of cooking recipes enriched with descriptions of intermediate steps that describe the input and output for each step. PizzaCommonsense serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit input-output descriptions to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized. GPT-4 achieves only 26\% human-evaluated preference for generations, leaving room for future improvements.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
