Understandable LLM guardrails via Symbolic Reasoning

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

LLMs are fast becoming ubiquitious. At the same time, there is significant concern about how malicious behaviour by these systems. This project will utilise techniques from symbolic AI, potentially including argumentation, plan recognition, and formal verification to limit the constrain the behaviour of LLMs making them more suitable for use in high risk settings. The PhD will consider individual LLMs as well as agentic LLMs and LLM societies.

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in Computing Science. We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Informal enquiries can be made by contacting Professor Oren (n.oren@abdn.ac.uk)

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen

References

• Landmark-based approaches for goal recognition as planning, RF Pereira, N Oren, F Meneguzzi, Artificial Intelligence 279, 103217
• Argument-based plan explanation, N Oren, K van Deemter, WW Vasconcelos, Knowledge Engineering Tools and Techniques for AI Planning, 173-188
• Explaining BDI agent behaviour through dialogue, LA Dennis, N Oren, 20th International Conference on Autonomous Agents and Multiagent Systems, 2021