Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
Eye movements in reading and information processing: 20 years of research
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
LLMs represent semantic relations geometrically via embedding distance and direction; a linear Polar Probe decodes these structures from middle-layer activations and generalizes to new entities.
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.
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.
citing papers explorer
-
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.
-
Polar probe linearly decodes semantic structures from LLMs
LLMs represent semantic relations geometrically via embedding distance and direction; a linear Polar Probe decodes these structures from middle-layer activations and generalizes to new entities.
-
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.
-
Time Series Forecasting Through the Lens of Dynamics
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.