Can AI Understand What We Cannot Say? Measuring Multilevel Alignment Through Abortion Stigma Across Cognitive, Interpersonal, and Structural Levels

As large language models increasingly mediate stigmatized health decisions, their capacity to genuinely understand complex psychological and physiological phenomena remains poorly evaluated. Can AI understand what we cannot say? We investigate whether LLMs coherently represent abortion stigma across the cognitive, interpersonal, and structural levels where it operates. We systematically tested 627 demographically diverse personas across five leading LLMs using the validated Individual Level Abortion Stigma Scale (ILAS). Our multilevel analysis examined whether models coherently represent stigma at the cognitive level (self-judgment), interpersonal level (worries about judgment and isolation), and structural level (community condemnation and disclosure patterns), as well as overall stigma. Models fail tests of genuine understanding across all levels. They overestimate interpersonal stigma while underestimating cognitive stigma, assume uniform community condemnation, introduce demographic biases absent from human validation data, miss the empirically validated stigma-secrecy relationship, and contradict themselves within theoretical constructs. These patterns reveal that current alignment approaches ensure appropriate language but not coherent multilevel understanding. This work provides empirical evidence that current LLMs lack coherent multilevel understanding of psychological and physiological constructs. AI safety in high-stakes contexts demands new approaches to design (multilevel coherence), evaluation (continuous auditing), governance and regulation (mandatory audits, accountability, deployment restrictions), and AI literacy in domains where understanding what people cannot say determines whether support helps or harms.

Adversarially Probing Cross-Family Sound Symbolism in 27 Languages

The phenomenon of sound symbolism, the non-arbitrary mapping between word sounds and meanings, has long been demonstrated through anecdotal experiments like Bouba Kiki, but rarely tested at scale. We present the first computational cross-linguistic analysis of sound symbolism in the semantic domain of size. We compile a typologically broad dataset of 810 adjectives (27 languages, 30 words each), each phonemically transcribed and validated with native-speaker audio. Using interpretable classifiers over bag-of-segment features, we find that phonological form predicts size semantics above chance even across unrelated languages, with both vowels and consonants contributing. To probe universality beyond genealogy, we train an adversarial scrubber that suppresses language identity while preserving size signal (also at family granularity). Language prediction averaged across languages and settings falls below chance while size prediction remains significantly above chance, indicating cross-family sound-symbolic bias. We release data, code, and diagnostic tools for future large-scale studies of iconicity.