AI RESEARCH
What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA
arXiv CS.AI
•
ArXi:2602.02834v3 Announce Type: replace-cross What structural inductive bias helps transformers reason over knowledge graphs? Through controlled ablations of a minimal transformer modification with four independently removable components (sparse adjacency masking, edge-type biases, query scaling, value gating), we isolate which structural signals drive multi-hop reasoning.