Spatial perspective transformation is a fundamental component of human spatial cognition, yet it remains unclear whether large language models (LLMs) can exhibit robust spatial reasoning abilities that support such transformations. We introduce a controlled dataset inspired by cognitive science studies, combining route-view and survey-view descriptions across multiple environmental topologies. Experiments on both open-source and closed-source LLMs show that models readily learn within-perspective reasoning but continue to struggle with cross-perspective transformation, especially from route-view to survey-view reasoning. The learnt capabilities remain strongly topology-dependent and generalise asymmetrically between within-perspective and cross-perspective settings. Scaling substantially improves allocentric and within-perspective reasoning, but does not uniformly resolve cross-perspective transformation difficulty, while chain-of-thought prompting provides little benefit. Overall, our results suggest that current LLMs do not consistently demonstrate perspective-invariant spatial reasoning across perspectives and environments. Code and datasets are available at https://github.com/zhanghaotong1/EMNLP-2026-perspective-transformation-in-LLMs.

Procedural text is a widely used genre that contains many steps of instructions of how to cook a dish or how to conduct a chemical experiment and analyze the procedural text has become a popular task in the NLP field. Since the procedural text can be very long and contains many details, summarizing the whole procedural text or giving an overview for each complicated procedure step can save time for readers and help them to capture the core information in the text. In this paper, we propose the procedural text summarization task with two summarization granularity: step-view and global-view, which summarizes each step in the procedural text separately or gives an overall summary for all steps respectively. To tackle this task, we propose an Entity-State Graph-based Summarizer (ESGS) which is based on state-of-the-art entity state tracking methods and constructs a heterogeneous graph to aggregate contextual information for each procedure. In order to help the summarization model focus on the salient entities, we propose to use the contextualized procedure graph representation to predict the salient entities. Experiments conducted on two datasets verify the effectiveness of our proposed model. Our code and datasets will be released on https://github.com/gsh199449/procedural-summ.