Do Language Models Know Who Did What to Whom?

Exposure is Optional: Learning Unlike Coordination in Language Models

Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics. A common view holds that only same-category constituents can be conjoined, which has been challenged by the many grammatical unlike coordinations found in natural language. Treating language models as a computational testbed, we investigate whether the acquisition of unlike coordination requires direct exposure in the training data, or whether it can emerge organically from general compositional abilities. Using Filtered-Corpus Training (FiCT), we train GPT-2 models on corpora from which all instances of unlike coordination have been removed. We find that direct exposure is not necessary: models trained on filtered data successfully generalize to unlike coordination, achieving perplexity and grammaticality judgments comparable to models trained on unfiltered text. Furthermore, our analyses of internal representations indicate that language models process unlike coordination by treating the conjoined elements as belonging to similar structural categories or through a mechanism akin to deletion, both of which appear learnable from exposure to alike coordination alone. This work contributes to the growing understanding of how language models internally represent linguistic structures, while also adding to the broader debate on coordination by showing how models generalize and process unlike coordination without direct exposure.

Do Language Models Know What Words Mean? Evaluating Semantic Knowledge of Adjective-Noun Compounds

Large Language Models as Distributional Baselines for Language Tasks

In order to ask questions about the mechanisms underpinning human cognition, researchers must control for properties of stimuli that could confound detected effects. In experiments involving linguistic stimuli, this includes properties like frequency, length, and neighborhood size of those stimuli, which are known to affect behavioral and neural responses. With improvements in the performance and usability of language models, it is now possible to also control for how predictable stimuli and their parts are, on the basis of the distributions of words alone: their distributional predictability. This coincides with a resurgence of interest in the possibility that statistical language learning may underlie a broad range of human cognitive phenomena; indeed, there are both theoretical and empirical reasons to believe that humans rely on distributional information during certain cognitive tasks. This creates a confound, whereby experimental operationalizations of psychological constructs with linguistic stimuli may not in fact be testing what they are intended to test. Thus, the central contributions of this paper are twofold: first, we articulate the conditions under which distributional predictability threatens the internal validity of an experiment; and second, we provide concrete recommendations for how to control for this potential confound. Beyond these primary contributions, we survey techniques for measuring distributional predictability, review theoretical and empirical work supporting the role of distributional statistics in human cognition, and present several case studies illustrating the range of possible outcomes—from the “distributional baselines” only marginally affecting theoretical inferences to constituting fully deflationary confounds. We also enumerate and address potential objections to this approach. This paper is primarily intended for researchers in psychology, cognitive science, and linguistics who use linguistic stimuli but have not yet incorporated distributional baselines into their work.

What does the general public want to know about language?

Abstract This study investigates how nonexperts conceptualize linguistics and what they most want to know about language. We recruited 812 English-speaking participants from Canada, the United States, and the United Kingdom via Prolific to complete four open-ended surveys (N = 406 on perceived professional foci; N = 406 on desired research topics). All responses were segmented into 2,684 statements and analyzed with unsupervised natural language processing: sentence embeddings (all-MiniLM-L6-v2) followed by k-means clustering, yielding 29 topic clusters. Results show that respondents broadly recognize core subfields (e.g., syntax, phonetics/phonology, morphology, semantics, historical linguistics) and also reproduce familiar misconceptions (e.g., linguists as translators; linguists as language or literature teachers). Public curiosity, however, concentrates on applied and experiential themes – language learning and learnability, bilingualism, dialect differences, and the origins, spread, and loss of languages. Topics linking variation, cognition, and development (sociolinguistics, acquisition, psycho-/neurolinguistics) form shared ground. We discuss how these high-interest domains can serve as entry points for communicating foundational linguistic concepts.

They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It

When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check. We treat the sender's communicative intent, the Gricean what-was-meant, as a first-class interpretability object, and show the failure is one of readout on top of a robust representation. A linear probe decodes the sender's intent, whether they want a thing recognized or evaluated, from a model's default-pass hidden states, cleanly and surface-independently, across six models and four families and in the base checkpoints. The representation generalizes further, to intent that is only pragmatically inferred, and to a second, lexically clean intent (support versus help). The behavioral half of the story, and every causal test, is established on the recognize/evaluate contrast, where what varies is whether the default output acts on the intent. The readout lags the representation in depth within a model (the intent is decodable several layers before it drives the output); across models, which ones act on it by default is model-specific, an observed stratification (three of six show the failure) that we do not read as a scaling law. Where the gap is open, a direction closely tied to the representation, the discriminative direction at a searched-for layer, is a causal handle: steering it recovers the intended behavior, as well as an explicit instruction does and with no prompt at all. This direction is near-orthogonal to the feedback-offering axis, so it routes a represented intent rather than a generic feedback knob, though at the recovery dose the routed intent can override an explicit request. We support each link with controls against obvious deflations and report the nulls as plainly as the confirmations.

Where did the ambiguity go? Examining how multimodal models interpret polysemous words

Human language is highly polysemous. Many common words (e.g.,"bank"or"palm") carry several distinct meanings that shape what humans communicate and imagine. Large language models (LLMs) have been shown to understand this multiplicity of meaning, but much less is known about how polysemy surfaces in other modalities such as images. We study this across 17 text-to-image and 15 text-generation models by giving each a polysemous word with no context to fix its meaning and measuring which senses are produced over many samples. We find a clear multimodal gap, where within every model family, generated images settle on far fewer senses than generated sentences (normalized entropy 0.10 vs. 0.25), and both are far less varied than what people imagine for the same words (normalized entropy 0.47). However, when we instead ask a model to list how often it would generate outputs corresponding to each possible meaning of a word, it predicts distributions that are more diverse than the actual space of outputs. These results reveal a multimodal gap in how foundation models express meaning, and how their understanding may not transfer faithfully nor equally across modalities.