Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.
A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing , booktitle =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
LLM surprisal and attention entropy replicate syncretism modulation of agreement attraction in English and German, align with null results in Turkish, and partially match Russian patterns.
citing papers explorer
-
Energy-Based Transformers as Predictors of Reading Difficulty
Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.
-
Syntactic Belief Update as the Driver of Garden Path Processing Difficulty
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
-
Quantifying the cross-linguistic effects of syncretism on agreement attraction
LLM surprisal and attention entropy replicate syncretism modulation of agreement attraction in English and German, align with null results in Turkish, and partially match Russian patterns.