mlsanityData to 14 Oct 2026

Bears, all bears, and some bears. Language Constraints on Language Models' Inductive Inferences

arXiv 2601.09852 ↗First posted 14 Jan 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 48 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

17 of 48 references.

References · 17

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  3. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237
  4. 2023Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationscited by 209
  5. 2022minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Modelscited by 58
  6. 2025How Linguistics Learned to Stop Worrying and Love the Language Modelscited by 51
  7. 2020Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humanscited by 42
  8. 2021Do language models learn typicality judgments from text?cited by 32
  9. 2021Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriouslycited by 18
  10. 2022Penguins Don't Fly: Reasoning about Generics through Instantiations and Exceptionscited by 17
  11. 2024DevBench: A multimodal developmental benchmark for language learningcited by 13
  12. 2024Characterizing the Role of Similarity in the Property Inferences of Language Modelscited by 11
5 more
  1. 2025Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter Itcited by 6
  2. 2025Representation biases: will we achieve complete understanding by analyzing representations?cited by 6
  3. 2025VAQUUM: Are Vague Quantifiers Grounded in Visual Data?cited by 4
  4. 2025VISaGE: Understanding Visual Generics and Exceptionscited by 4
  5. 2024Generics are puzzling. Can language models find the missing piece?cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The in-context inductive biases of vision-language models differ across modalities
  2. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  3. 2023What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?
  4. 2023Hypothesis Search: Inductive Reasoning with Language Models
  5. 2024On the Role of Model Prior in Real-World Inductive Reasoning
  6. 2023A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
  7. 2025Relational reasoning and inductive bias in transformers and large language models
  8. 2026Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs