Thesis Description & Objectives
LLMs are powerful — until accuracy becomes non-negotiable. In regulated domains like insurance, compliance, or legal advisory, a single hallucinated value carries real financial and legal consequences. Yet current approaches to grounding LLM behavior
— prompt engineering, fine-tuning, RLHF — offer probabilistic guarantees at best. The gap between “usually correct” and “provably correct” remains wide open.
This thesis aims to close that gap by investigating neuro-symbolic architectures that enforce hard, verifiable constraints on LLM outputs — combining the generative fluency of modern GenAI with the logical rigor of symbolic reasoning. The candidate
will build and benchmark constrained pipelines capable of producing structured, traceable, auditable responses, and stress-test them against adversarial inputs designed to break compliance. There is the possibility to collaborate with the creator of
one of the core neuro-symbolic frameworks.
