Mamba's per-word timesteps significantly predict human reading times beyond GPT-2 surprisal in a naturalistic dataset.
arXiv preprint arXiv:2502.01615 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3representative citing papers
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
HybridMoE with controlled hybridization and idiomatic property signals yields 5-6% gains in figurative language representation for multilingual vision-language models.
citing papers explorer
-
Timesteps of Mamba Align with Human Reading Times
Mamba's per-word timesteps significantly predict human reading times beyond GPT-2 surprisal in a naturalistic dataset.
-
Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
-
When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models
HybridMoE with controlled hybridization and idiomatic property signals yields 5-6% gains in figurative language representation for multilingual vision-language models.