Humans naturally interpret numbers non-literally, effortlessly combining context, world knowledge, and speaker intent. We investigate whether large language models (LLMs) interpret numbers similarly, focusing on hyperbole and pragmatic halo effects. Through systematic comparison with human data and computational models of pragmatic reasoning, we find that LLMs diverge from human interpretation in striking ways. By decomposing pragmatic reasoning into testable components, grounded in the Rational Speech Act framework, we pinpoint where LLM processing diverges from human cognition -- not in prior knowledge, but in reasoning with it. This insight leads us to develop a targeted solution -- chain-of-thought prompting inspired by an RSA model makes LLMs' interpretations more human-like. Our work demonstrates how computational cognitive models can both diagnose AI-human differences and guide development of more human-like language understanding capabilities.

Large language models (LLMs) are trained on data assumed to include natural language pragmatics, but do they actually behave like pragmatic speakers? We attempt to answer this question using the Rational Speech Act (RSA) framework [9, 10], which models pragmatic reasoning in human communication. Using the paradigm of a reference game constructed from the TUNA [27] corpus, we score candidate referential utterances in both a state-of-the-art LLM (Llama3-8B-Instruct) and in the RSA model, comparing and contrasting these scores. Given that RSA requires defining alternative utterances and a truth-conditional meaning function, we explore such comparison for different choices of each of these requirements. We find that while scores from the LLM have some positive correlation with those from RSA, there isn't sufficient evidence to claim that it behaves like a pragmatic speaker. This initial study paves way for further targeted efforts exploring different models and settings, including human-subject evaluation, to see if LLMs truly can, or be made to, behave like pragmatic speakers.

The Rational Speech Act (RSA) model provides a flexible framework to model pragmatic reasoning in computational terms. However, state-of-the-art RSA models are still fairly distant from modern machine learning techniques and present a number of limitations related to their interpretability and scalability. Here, we introduce a new RSA framework for metaphor understanding that addresses these limitations by providing an explicit formula - based on the mutually shared information between the speaker and the listener - for the estimation of the communicative goal and by learning the rationality parameter using gradient-based methods. The model was tested against 24 metaphors, not limited to the conventional $\textit{John-is-a-shark}$ type. Results suggest an overall strong positive correlation between the distributions generated by the model and the interpretations obtained from the human behavioral data, which increased when the intended meaning capitalized on properties that were inherent to the vehicle concept. Overall, findings suggest that metaphor processing is well captured by a typicality-based Bayesian model, even when more scalable and interpretable, opening up possible applications to other pragmatic phenomena and novel uses for increasing Large Language Models interpretability. Yet, results highlight that the more creative nuances of metaphorical meaning, not strictly encoded in the lexical concepts, are a challenging aspect for machines.