Score: 0

Less is more: Probabilistic reduction is best explained by small-scale predictability measures

Published: December 29, 2025 | arXiv ID: 2512.23659v1

By: Cassandra L. Jacobs , Andrés Buxó-Lugo , Anna K. Taylor and more

Potential Business Impact:

Finds how much language models need to think.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇺🇸 United States

Page Count
13 pages

Category
Computer Science:
Computation and Language