Jakub Dotlacil

Lexical and Discourse Semantics in a Reading-time Corpus of English

Relational Attention for Data-Efficient Language Modeling

Relational BabyLM is a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single decoder-only Transformer, and introduces a novel symbol-retrieval mechanism that matches learned symbol libraries while adding no parameters.

When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs

Psycholinguistics studies show that human readers fall for coherence illusions: an incoherent discourse can seem coherent simply because a distractor matches what comes next. We investigate whether Dutch language models (6 monolingual and 4 multilingual) show the same behavior on texts that link back to earlier context...

Energy-Based Transformers as Predictors of Reading Difficulty

Evidence is found that energy may serve as a single unified predictor where multiple complementary measures have previously been required, suggesting that energy may serve as a single unified predictor where multiple complementary measures have previously been required.