Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Relational Attention for Data-Efficient Language Modeling
Adrian Brasoveanu, Ece Takmaz, Jakub Dotlačil
We present Relational BabyLM, a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single decoder-only Transformer. Archit…
cs.CL2026
When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs
Ece Takmaz, Nitin Kumar, Li Kloostra +1
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 in…
cs.CL2026
Energy-Based Transformers as Predictors of Reading Difficulty
Jakub Dotlacil, Ece Takmaz
Transformer language models have become established tools for modeling human sentence processing, with measures such as surprisal and attention entropy serving as effective predict…