Is analogy enough to draw novel adjective-noun inferences?
This addresses a foundational question in cognitive science and AI about the mechanisms of generalization, showing that analogy is insufficient for some novel inferences, which is incremental but clarifies prior claims.
The study investigated whether analogy alone can explain how humans and large language models (LLMs) infer meanings for novel adjective-noun combinations, finding that while analogy works for many cases, it fails for some where both humans and LLMs converge on inferences, suggesting composition is also involved.
Recent work (Ross et al., 2025, 2024) has argued that the ability of humans and LLMs respectively to generalize to novel adjective-noun combinations shows that they each have access to a compositional mechanism to determine the phrase's meaning and derive inferences. We study whether these inferences can instead be derived by analogy to known inferences, without need for composition. We investigate this by (1) building a model of analogical reasoning using similarity over lexical items, and (2) asking human participants to reason by analogy. While we find that this strategy works well for a large proportion of the dataset of Ross et al. (2025), there are novel combinations for which both humans and LLMs derive convergent inferences but which are not well handled by analogy. We thus conclude that the mechanism humans and LLMs use to generalize in these cases cannot be fully reduced to analogy, and likely involves composition.