conftrace_

surprisal estimation

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reading time (3) language model (3) character model (1) neural language processing (1) human sentence processing (1) large language model (1) bpe tokenization (1) reading time prediction (1) lexical uncertainty (1) structural processing model (1)

Papers

Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly EACL 2026 Word Surprisal Correlates with Sentential Contradiction in LLMs EACL 2026 Temperature-scaling surprisal estimates improve fit to human reading times – but does it do so for the “right reasons”? ACL 2024 Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship? EMNLP 2023 Surprisal Estimators for Human Reading Times Need Character Models ACL 2021