Abstract:Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of experiences, affect, and social context. Do large language models (LLMs) ground abstract concepts in a similar way? We study this by replicating property-generation experiments from cognitive science on 21 frontier and open-weight LLMs. Across models and experiments, we find a consistent pattern: when compared to humans, models rely too heavily on word associations, and underproduce properties tied to emotion and internal states. This yields a large and consistent grounding gap: no model exceeds a Pearson correlation r=0.37 with human responses, compared to a human-to-human ceiling above r=0.9. To better interpret this gap, we also replicate a rating experiment on grounding categories and find that here LLMs align more closely with human judgment, and alignment improves as models get larger. We then use sparse autoencoders (SAEs) to inspect whether this information is also reflected in the models' internal features, and we do identify features connected to grounding dimensions such as "sensorimotor" and "social". These findings suggest that current LLMs can recover grounding dimensions when explicitly queried, but do not recruit them in a human-like way when words are generated freely.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08837 [cs.CL] |
| (or arXiv:2605.08837v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08837 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Orfeas Menis Mastromichalakis [view email]
[v1]
Sat, 9 May 2026 09:41:12 UTC (275 KB)