AI RESEARCH
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
arXiv CS.AI
•
ArXi:2605.08716v1 Announce Type: new Are certain cognitive biases mathematically inevitable consequences of sequential information processing? We prove that primacy effects, anchoring, and order-dependence are architecturally necessary in autoregressive language models due to causal masking constraints.