Conversational Implicatures through the Lens of LLMs

Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension

This work systematically vary the context window size of GPT-2 across four large-scale naturalistic English reading-time datasets and observes a U-shaped relationship, demonstrating that tracking long-range coreference relations is one important factor for the alignment between LM surprisal and human reading behavior.

Beyond Literal Meaning: How LLMs Interpret Yemeni Proverbs

Results show that instruction-tuned models like GPT-4o and Gemini 1.5 Pro outperform smaller models in both automatic and human evaluations, and LLM-as-a-Judge evaluation correlates strongly with human assessment.

Pragmatics beyond humans: meaning, communication, and LLMs

The paper argues that the emergence of large language models (LLMs) requires a conceptual and methodological reconsideration of pragmatics. It first challenges the traditional positioning of pragmatics within the semiotic trichotomy of syntax, semantics, and pragmatics, suggesting that the Human–Machine Communication (...

On Modeling Dative Alternations in Large Language Models

Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation

This work tested humans and vision--language models on their ability to identify the intended meaning of descriptions produced in iterated reference games, varying the provided context in terms of amount, order, and relevance.

Rethinking Linguistic Tests for Large Language Models: Airplanes Aren't Birds

This article challenges the growing trend of using traditional linguistic tests to evaluate Large Language Models (LLMs), arguing that this approach fundamentally misunderstands both the purpose of these tests and the nature of LLMs. As a result, such evaluations often yield misleading conclusions, answering no real qu...