conftrace_

surprisal estimate

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

word predictability (1) human reading time (1) reading time (1) subword tokenization (1) bpe tokenizer (1) language model (1) psycholinguistic modeling (1) self-attention mechanism (1) transformer architecture (1)

Papers

Word predictability estimates from language models are not robust to tokenizer vocabulary CoNLL 2026 Locally Biased Transformers Better Align with Human Reading Times ACL 2024