LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
The shrink- ing landscape of linguistic diversity in the age of large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Language is far more than a communication tool. A wealth of information - including but not limited to the identities, psychological states, and social contexts of its users - can be gleaned through linguistic markers, and such insights are routinely leveraged across diverse fields ranging from product development and marketing to healthcare. In four studies utilizing experimental and observational methods, we demonstrate that the widespread adoption of large language models (LLMs) as writing assistants is linked to notable declines in linguistic diversity and may interfere with the societal and psychological insights language provides. We show that while the core content of texts is retained when LLMs polish and rewrite texts, not only do they homogenize writing styles, but they also alter stylistic elements in a way that selectively amplifies certain dominant characteristics or biases while suppressing others - emphasizing conformity over individuality. By varying LLMs, prompts, classifiers, and contexts, we show that these trends are robust and consistent. Our findings highlight a wide array of risks associated with linguistic homogenization, including compromised diagnostic processes and personalization efforts, the exacerbation of existing divides and barriers to equity in settings like personnel selection where language plays a critical role in assessing candidates' qualifications, communication skills, and cultural fit, and the undermining of efforts for cultural preservation.
years
2026 5representative citing papers
AI writing assistance systematically distorts how writers are perceived across 29 social dimensions, and mitigating undesirable distortions reduces user preference for AI-assisted text.
Multi-turn simulations of grounded support narratives show LLMs reduce teaching-oriented responses as estimated user distress rises, with community context also shaping strategy choice.
Self-training restructures language by amplifying surface markers and collapsing deep syntax according to structural depth rather than frequency, as evidenced by correlations across multiple models and a human fine-tuning control.
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.
citing papers explorer
-
AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable
LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
-
Measuring and Mitigating Persona Distortions from AI Writing Assistance
AI writing assistance systematically distorts how writers are perceived across 29 social dimensions, and mitigating undesirable distortions reduces user preference for AI-assisted text.
-
Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation
Multi-turn simulations of grounded support narratives show LLMs reduce teaching-oriented responses as estimated user distress rises, with community context also shaping strategy choice.
-
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
Self-training restructures language by amplifying surface markers and collapsing deep syntax according to structural depth rather than frequency, as evidenced by correlations across multiple models and a human fine-tuning control.
-
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.