CLDec 29, 2025
Less is more: Probabilistic reduction is best explained by small-scale predictability measures
arXiv:2512.23659v2
Originality Synthesis-oriented
AI Analysis
This addresses methodological questions for researchers studying language model probabilities and cognitive phenomena, though it appears incremental.
The paper investigated whether whole utterances are necessary to observe probabilistic reduction in language models, finding that n-gram representations suffice as cognitive units of planning.
The primary research questions of this paper center on defining the amount of context that is necessary and/or appropriate when investigating the relationship between language model probabilities and cognitive phenomena. We investigate whether whole utterances are necessary to observe probabilistic reduction and demonstrate that n-gram representations suffice as cognitive units of planning.