impossibility-theorems

Tag

Cards List
#impossibility-theorems

Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation

arXiv cs.AI · yesterday Cached

This paper proves impossibility theorems showing that primacy effects, anchoring, and order-dependence are architecturally necessary biases in autoregressive language models due to causal masking constraints. The authors validate these theoretical bounds across 12 frontier LLMs and confirm related predictions through pre-registered human experiments involving working memory loads.

0 favorites 0 likes
← Back to home

Submit Feedback