Mandelkern and Linzen (2024) argue that words generated by language models (LMs) are linked to causal histories of use within human linguistic communities, and ultimately to their referents. Therefore, LMs’ words refer. We qualify Mandelkern and Linzen’s claim as applicable to a narrow class of expressions. Thus qualified, the claim is valid and motivated by the need to evaluate LMs’ outputs for relevance and truth. Next, we discuss the actual scope of their claim, and we conclude that the bounds of sense and reference in LMs are more restricted than in humans. We close with some considerations on the status of LMs as members of human linguistic communities.

In complement coercion sentences, like John began the book, a covert event (e.g., reading) may be recovered based on lexical meanings, world knowledge, and context. We investigate how context influences coercion interpretation performance for 17 language models (LMs) in Norwegian, a low-resource language. Our new dataset contained isolated coercion sentences (context-neutral), plus the same sentences with a subject NP that suggests a particular covert event and sentences that have a similar effect but that precede or follow the coercion sentence. LMs generally benefit from contextual enrichment, but performance varies depending on the model. Models that struggled in context-neutral sentences showed greater improvements from contextual enrichment. Subject NPs and pre-coercion sentences had the largest effect in facilitating coercion interpretation.

In sentences such as John began the book, the complement noun, lexically denoting an entity, is interpreted as an event. This phenomenon is known in linguistics as complement coercion: the event associated with the verb is not overtly expressed but can be recovered from the meanings of other constituents, context and world knowledge. We investigate whether language models (LMs) can exploit sentence structure and compositional meaning to recover plausible events in complement coercion. For the first time, we tested different LMs in Norwegian, a low-resource language with high syntactic variation in coercion constructions across aspectual verbs. Results reveal that LMs struggle with retrieving plausible events and with ranking them above less plausible ones. Moreover, we found that LMs do not exploit the compositional properties of coercion sentences in their predictions.