Later LLM layers align better with human cognitive effort in syntactic ambiguity than early layers do, indicating dual processing modes and complementary benefits from multi-layer probability updates.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Early layers of language models predict early-pass human reading times better than surprisal, with surprisal superior for late-pass measures and strong variation by language.
citing papers explorer
-
Dual Alignment Between Language Model Layers and Human Sentence Processing
Later LLM layers align better with human cognitive effort in syntactic ambiguity than early layers do, indicating dual processing modes and complementary benefits from multi-layer probability updates.
-
Probing for Reading Times
Early layers of language models predict early-pass human reading times better than surprisal, with surprisal superior for late-pass measures and strong variation by language.