The paper examines how users’ prompts to large language models evolve over time, applying speech act and politeness theory to a corpus of 2,000 English prompts from 2023 and 2025. It finds a shift toward more indirect, implicit, and fragmentary directive speech acts, with a notable 14.9‑percentage‑point drop in explicit propositional content and a decline in politeness markers. This suggests users increasingly rely on the model’s inferential abilities, treating it as a competent implicature resolver.
arXiv:2606. 01845v1 Announce Type: cross Abstract: Although large language models (LLMs) have shown considerable progress in pragmatic language understanding, prior research has focused mainly on their comprehension of verbal behavior.
The paper investigates whether large language models (LLMs) assess politeness in ways that match human judgments. Using two English datasets—one with continuous ratings and another with three‑way categorical labels—the authors compare seven LLMs to human annotations. They find that models agree more with each other than with humans, show systematic neutral bias in categorical predictions, and that alignment varies with explicit linguistic cues and rapport‑building strategies.
arXiv:2606. 08076v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
The paper investigates whether large language models (LLMs) assess politeness in ways that match human judgments. Using two English datasets—one with continuous ratings and another with three‑way categorical labels—the authors find that LLMs agree more with each other than with humans. They observe that model–human alignment depends on explicit linguistic cues, while misaligned cases often involve rapport‑building strategies. Additionally, models tend to overproduce Neutral labels and underpredict Impolite labels, a pattern that persists even when expert consensus is used as a reference.
arXiv:2605.28782v2 Announce Type: replace Abstract: Discourse particles, such as well and kind of, are crucial components that enable LLMs to "speak" more like humans. They are used to convey emotion...
arXiv:2606. 08076v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
arXiv:2604. 02512v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning.
The study investigates how large language models (LLMs) handle deontic modal verbs such as must, should, and have to, comparing AI-generated text to contemporary human usage across multiple corpora. Results show that LLMs consistently underuse positive deontic modals relative to modern informal digital contexts, though their modal frequencies align with formal published English from the 20th century. The underuse is most pronounced in constructions tied to interpersonal stance, while LLMs match or exceed human usage in instructional or question‑answering contexts, suggesting genre‑dependent modal profiles.
The paper investigates how the way users phrase advice‑seeking requests—termed articulation—creates stable, measurable patterns distinct from the topics of the requests. By analyzing 16,447 prompts from public chat corpora, the authors identify a small set of latent articulation factors that consistently appear across datasets and splits. One key finding is a long‑form, information‑poor style that leads language models to give shorter, vaguer answers without seeking clarification, a pattern that persists across topics and prompt lengths.
arXiv:2602.21223v2 Announce Type: replace Abstract: It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like ``This is urgent'' or ``As your...
Full‑duplex speech models can listen and speak simultaneously, but they struggle to decide when to speak. Experiments with five model families show that being addressed or encountering silence are reliable triggers, whereas cues like false facts or hazards are not. Even when models answer questions, they rarely challenge false claims or warn about danger, revealing a gap in content understanding and intervention decisions.
arXiv:2607. 25094v1 Announce Type: cross Abstract: Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users.