LLM-based surprisal is not interchangeable across models: different architectures compute word probabilities via visibly different internal computations, undermining representation-agnostic claims for Surprisal Theory.
Noisy-context surprisal as a human sentence processing cost model , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
surprisal is Not a Theory
LLM-based surprisal is not interchangeable across models: different architectures compute word probabilities via visibly different internal computations, undermining representation-agnostic claims for Surprisal Theory.