AINeutralarXiv – CS AI · 8h ago6/10
🧠
The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs
Researchers demonstrate that persistent homology—a topological data analysis technique—can detect and classify ill-posed questions (ambiguous, underspecified, or contradictory queries) in large language models by analyzing hidden state geometry across transformer layers. The method achieves 78-88% accuracy on benchmark datasets and enables targeted activation steering to improve response quality, offering a principled approach to handling inherently problematic inputs.