PhD Opportunity: Neurosymbolic Spatial Reasoning

Teaching language models to plan over qualitative geographic knowledge

SchoolSchool of Computational and Mathematical Sciences, Cardiff University
SupervisorsDr Alia I. Abdelmoty
Start dateOctober 2027
FundingCardiff University and China Scholarship Council (CSC) Research Excellence Scholarships. Self-funded applicants and applicants with other funding are also welcome.
CSC deadline3 November 2026
Contactabdelmotyai@cardiff.ac.uk

About the Project

Large language models are fluent but unreliable at spatial reasoning. Given a geographic knowledge graph, they recall isolated facts well, yet they struggle with questions that require several spatial relationships to be chained together. They also cannot reliably write the formal spatial queries that would let a database reason on their behalf.

Part of the difficulty lies in how geographic knowledge is represented. In most geographic knowledge graphs, spatial relationships are computed in advance from geometry and stored as flat facts. Systems built on them are therefore tested on retrieving stored answers, not on reasoning.

This project takes a different route. It does not ask the model to compute geometry or to write database queries. It investigates whether a model can generate abstract, verifiable reasoning programs over a compact vocabulary of qualitative spatial relations (containment, adjacency, proximity and direction). A symbolic engine then executes each program and checks its result, so that every answer can be traced to the relations that support it.

The central question is whether a small, closed and compositional target language makes spatial reasoning at inference time tractable where general query generation has failed. The work combines current research on language models with knowledge representation and qualitative spatial reasoning, and its results are relevant wherever people need trustworthy answers to questions about places.

Research Questions

What You Will Do

You will design the target reasoning language and the methods by which a language model produces programs in it. You will build the symbolic component that executes and verifies those programs over geographic knowledge graphs, and you will evaluate the combined system against established geographic question-answering approaches. There is room to shape the direction of the project around your own strengths, whether these lie in machine learning, in knowledge graphs or in formal reasoning.

You will join a research group with a long record in qualitative spatial reasoning, place ontologies and geographic knowledge graphs, and you will be able to draw on its existing work as a starting point.

Candidate Profile

We are looking for a candidate with a strong background in computer science, artificial intelligence or a related quantitative discipline. Solid programming skills in Python and familiarity with machine learning are expected. Experience with large language models, knowledge graphs, semantic web technologies or symbolic reasoning is an advantage. An interest in combining neural and symbolic methods is essential. No prior training in geography is required.

Where This Project Sits in Our Research

The project builds on a long line of research at Cardiff on qualitative spatial representation and reasoning, place ontologies and geographic knowledge graphs. Our current work centres on the Qualitative Place Model (QPM), an ontology that represents the location of a place through relations of containment, adjacency, proximity and direction, without relying on coordinate geometry. The ontology is openly available at github.com/Aliaia/qpm.

The PhD project is not tied to this model. QPM is one example of the class of qualitative relational representations the project studies, and it offers a published ontology and evaluation instrument to start from.

Funding

This project is available under the Cardiff University and China Scholarship Council (CSC) Research Excellence Scholarships for entry in October 2027. Successful applicants receive CSC funding that covers airfares and living costs, and Cardiff University provides a tuition fee waiver. Candidates are nominated by the School and the University and are then reviewed by the CSC.

The project is also open to self-funded applicants and to applicants who hold, or are applying for, funding from other sources.

Eligibility for the CSC Scholarship

Applicants must be Chinese nationals without permanent residency in a foreign country and must not be over 35 years of age. Students already registered on a PhD pathway or programme at Cardiff University are not eligible.

Applicants should hold, or be about to obtain, a first class or upper second class (2:1) bachelor's degree or a master's degree in a relevant discipline. The School applies the following additional expectations:

These additional expectations can be relaxed for exceptional applicants, for example those with strong publications, strong industry experience or prestigious awards.

CSC applicants need IELTS 6.5 overall with at least 6.0 in each subskill, or an equivalent score in another test accepted by the University. A degree taught in English and awarded by a UK institution may exempt an applicant from the test. A test certificate must still be valid at the start of the programme in October 2027. Evidence should be submitted by 8 December 2026 where possible and no later than 5 January 2027.

How to Apply

Please contact Dr Abdelmoty at abdelmotyai@cardiff.ac.uk before applying, with your CV, transcripts and a short note on why this topic appeals to you.

Submit a PhD application through the Cardiff University Computer Science and Informatics programme page, choosing Doctor of Philosophy and Full-Time. Name this project title and Dr Abdelmoty as the proposed supervisor.

CSC applicants should choose the October 2027 start date and state in the funding section that they wish to be considered for the Cardiff University China Scholarship Council funding. The application must include an academic CV and a personal statement that sets out your research interest, the preparation you have undertaken and your understanding of the significance of the research. The deadline for CSC applications is 3 November 2026, and nominated applicants will be interviewed by a School panel.

Self-funded applicants and applicants with other funding should state their source of funding in the funding section. Please get in touch to discuss entry requirements and start dates.

Selected Publications from the Group

References