AI alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms, values, and goals. Alignment is now central to research on foundation models and AI agents. Most recent work focuses on methods to prevent potentially harmful biases, account for social inequalities, improve AI safety, and enhance explainability. Notably, the debiasing 'corrections' applied to various stages of AI/ML workflows may lead to outcomes that diverge strongly from current statistical realities on the ground. For instance, text-to-image models may depict a balanced gender ratio of company leadership, despite existing imbalances. However, an often overlooked dimension is the geographic variability of alignment. What is considered appropriate, truthful, or legal can vary greatly between regions due to cultural differences, political realities, or legislation. Hence, some model outputs align without further knowledge of the user's geospatial context, while others are highly sensitive to it. Put differently, whether these outputs align varies geographically. E.g., statements about Kashmir cannot be generated without understanding the user's origin and current location. From a common-sense perspective, this problem is hardly new. In fact, Google Maps will render different administrative borders based on the user's location. Interestingly, in both knowledge representation and representation learning, spatiotemporal context, e.g., due to the monotonic nature of reasoning, remains a major challenge. Until very recently, these were largely theoretical problems. What is truly novel is the scale and level of automation at which AI systems now mediate knowledge, express opinions, and represent reality to millions of users across borders, often with little transparency or oversight regarding how context is handled. With agentic AI on the horizon, the urgency for pluralistic, geographically aware alignment, rather than one-size-fits-all solutions, is growing. Here, we motivate and formalize the vision of geo-alignment, outline how it goes beyond pluralistic alignment by offering learnable spatially explicit patterns, and suggest concrete avenues for future research.

AI foundation models have demonstrated some capabilities for the understanding of geospatial semantics. However, applying such pre-trained models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of complex spatial relations. To address these issues, we investigate the extent to which a well-known-text (WKT) representation of geometries and their spatial relations (e.g., topological predicates) are preserved during spatial reasoning when the geospatial vector data are passed to large language models (LLMs) including GPT-3.5-turbo, GPT-4, and DeepSeek-R1-14B. Our workflow employs three distinct approaches to complete the spatial reasoning tasks for comparison, i.e., geometry embedding-based, prompt engineering-based, and everyday language-based evaluation. Our experiment results demonstrate that both the embedding-based and prompt engineering-based approaches to geospatial question-answering tasks with GPT models can achieve an accuracy of over 0.6 on average for the identification of topological spatial relations between two geometries. Among the evaluated models, GPT-4 with few-shot prompting achieved the highest performance with over 0.66 accuracy on topological spatial relation inference. Additionally, GPT-based reasoner is capable of properly comprehending inverse topological spatial relations and including an LLM-generated geometry can enhance the effectiveness for geographic entity retrieval. GPT-4 also exhibits the ability to translate certain vernacular descriptions about places into formal topological relations, and adding the geometry-type or place-type context in prompts may improve inference accuracy, but it varies by instance. The performance of these spatial reasoning tasks unveils the strengths and limitations of the current LLMs in the processing and comprehension of geospatial vector data and offers valuable insights for the refinement of LLMs with geographical knowledge towards the development of geo-foundation models capable of geospatial reasoning.

Intuitively, there is a relation between measures of spatial dependence and information theoretical measures of entropy. For instance, we can provide an intuition of why spatial data is special by stating that, on average, spatial data samples contain less than expected information. Similarly, spatial data, e.g., remotely sensed imagery, that is easy to compress is also likely to show significant spatial autocorrelation. Formulating our (highly specific) core concepts of spatial information theory in the widely used language of information theory opens new perspectives on their differences and similarities and also fosters cross-disciplinary collaboration, e.g., with the broader AI/ML communities. Interestingly, however, this intuitive relation is challenging to formalize and generalize, leading prior work to rely mostly on experimental results, e.g., for describing landscape patterns. In this work, we will explore the information theoretical roots of spatial autocorrelation, more specifically Moran's I, through the lens of self-information (also known as surprisal) and provide both formal proofs and experiments.

The term between is frequently used to describe spatial arrangements of objects where one described core object is positioned in the space bounded by two or more peripheral objects. As such, the relation between involves spatial configurations of at least three spatial objects. However, most of the existing qualitative spatial reasoning models focus only on binary spatial relations, and there is currently no single model that enables adequate reasoning about this ternary spatial relation. This paper proposes a novel model for expressing nuanced spatial relationships between three spatial objects, called the Ray Intersection Model (RIM). RIM evaluates rays cast between two peripheral spatial objects, and their topological relations with the core object to determine its position relative to the peripheral objects. RIM leaves the binary classification of the core object as between/not between to the user and application context. Although RIM supports all types of 2D spatial objects (i.e. points, lines, and polygons), its expressiveness is demonstrated in this paper by analyzing the total of 28 distinct configurations of triplets of polygon objects in a 2D plane. RIM has been computationally implemented and we demonstrate how RIM can be applied to analyze the arrangements of buildings at a university campus.