In this paper, we evaluate the use of style embeddings for distinguishing machine-generated from human-written text. Style embeddings are particularly suited for this task as compared to semantic embeddings, they offer higher content-independence, and compared to feature-engineering approaches, they offer a richer and more holistic representation of writing style. We use a detection module in which texts are first embedded in high-dimensional stylistic spaces using a style encoder, and the resulting vector representations are classified using supervised methods. To optimize this detector, we evaluate the performance of a range of pre-trained public-domain style encoders paired with different supervised methods. When evaluated on MGTBench, a widely adopted benchmark, our approach matches or exceeds state-of-the-art performance metrics. It also generalizes well across various text domains and LLMs. Our findings highlight the potential, and would facilitate the use, of style embeddings as lightweight and effective components of machine-generated text detection systems.

Large language models encode high-level concepts with heterogeneous domain-specific manifestations, but it remains unclear whether their internal representations are organized in a form that supports cross-domain generalization. We investigate this question by adapting representational geometry methods from systems neuroscience and using political ideology as a naturalistic test case for a candidate latent variable spanning diverse policy domains. Across three open-weight LLMs, we analyze hidden states elicited by matched left- and right-leaning statements from ten policy domains. Within each domain, while political polarity is linearly decodable, lexical features achieve comparable performance. By contrast, cross-domain generalization substantially exceeds the lexical baseline and peaks in intermediate layers. This peak coincides with a marked reduction in participation ratio, suggesting that domain-specific political distinctions, instead of being maintained as independent axes, become aligned within a shared low-dimensional subspace. These findings suggest that LLMs transiently organize heterogeneous inputs into a common representational geometry that supports cross-domain abstraction, offering insight into how models structure complex social knowledge.

Language Style Matching (LSM)—the subconscious alignment of linguistic style between conversational partners—is a key indicator of social coordination in human dialogue. We present the first systematic study of LSM in Large Language Models (LLMs) focusing on two primary objectives: measuring the degree of LSM exhibited in LLM-generated responses and developing techniques to enhance it. First, in order to measure whether LLMs natively show LSM, we computed LIWC-based LSM scores across diverse interaction scenarios and found that LSM scores for text generated by LLMs were either below or near the lower range of such scores observed in human dialogue. Second, we show that LLMs’ adaptive behavior in this regard can be improved using inference-time techniques. We introduce and evaluate an inference-time sampling strategy—Logit-Constrained Generation—which can substantially enhance LSM scores in text generated by an LLM while preserving fluency. By advancing our understanding of LSM in LLMs and proposing effective enhancement strategies, this research contributes to the development of more socially attuned and communicatively adaptive AI systems.

This study investigates differences in linguistic accommodation—changes in language use and style that individuals make to align with their dialogue partners—in human and LLM communication. Specifically, it contrasts semantic and stylistic alignment within question-answer pairs in terms of whether the answer was given by a human or an LLM. Utilizing embedding-based measures of linguistic similarity, we find that LLM-generated answers demonstrate higher semantic similarity—reflecting close conceptual alignment with the input questions—but relatively lower stylistic similarity. Human-written answers exhibit a reverse pattern, with lower semantic but higher stylistic similarity to the respective questions. These findings point to contrasting linguistic accommodation strategies evident in human and LLM communication, with implications for furthering personalization, social attunement, and engagement in human-AI dialogue.