Guardado en:
Detalles Bibliográficos
Autores principales: Padmanabhan, Sriram, Song, Siyuan, Misra, Kanishka
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.09852
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917222988906496
author Padmanabhan, Sriram
Song, Siyuan
Misra, Kanishka
author_facet Padmanabhan, Sriram
Song, Siyuan
Misra, Kanishka
contents Language places subtle constraints on how we make inductive inferences. Developmental evidence by Gelman et al. (2002) has shown children (4 years and older) to differentiate among generic statements ("Bears are daxable"), universally quantified NPs ("all bears are daxable") and indefinite plural NPs ("some bears are daxable") in extending novel properties to a specific member (all > generics > some), suggesting that they represent these types of propositions differently. We test if these subtle differences arise in general purpose statistical learners like Vision Language Models, by replicating the original experiment. On tasking them through a series of precondition tests (robust identification of categories in images and sensitivities to all and some), followed by the original experiment, we find behavioral alignment between models and humans. Post-hoc analyses on their representations revealed that these differences are organized based on inductive constraints and not surface-form differences.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09852
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bears, all bears, and some bears. Language Constraints on Language Models' Inductive Inferences
Padmanabhan, Sriram
Song, Siyuan
Misra, Kanishka
Computation and Language
Language places subtle constraints on how we make inductive inferences. Developmental evidence by Gelman et al. (2002) has shown children (4 years and older) to differentiate among generic statements ("Bears are daxable"), universally quantified NPs ("all bears are daxable") and indefinite plural NPs ("some bears are daxable") in extending novel properties to a specific member (all > generics > some), suggesting that they represent these types of propositions differently. We test if these subtle differences arise in general purpose statistical learners like Vision Language Models, by replicating the original experiment. On tasking them through a series of precondition tests (robust identification of categories in images and sensitivities to all and some), followed by the original experiment, we find behavioral alignment between models and humans. Post-hoc analyses on their representations revealed that these differences are organized based on inductive constraints and not surface-form differences.
title Bears, all bears, and some bears. Language Constraints on Language Models' Inductive Inferences
topic Computation and Language
url https://arxiv.org/abs/2601.09852