Iterative Matrix Steering: Forcing LLMs to "Rationalize" Hallucinations via Subspace Alignment
This work was motivated by following publication Mechanistically Eliciting Latent Behaviors — rely primarily on static steering vectors: h′=h+α⋅v When i get known about steering vectors as conceptual possibility i had idea to try to change knowledge i llm using only math and statistic and avoid uses gradient descend. And...
Dec 23, 202510