How desirable is alignment between LLMs and linguistically diverse human users?

TL;DR

The paper examines whether LLMs should align their language output to linguistically diverse users defined by age, gender, and multilingual experience, synthesizing psycholinguistic findings on how processing varies across these dimensions. It discusses alignment from both human communication and human–computer interaction perspectives, highlighting structural priming, neural coupling, and the potential for user modeling to improve usability while also risking homogenization and bias. The authors argue for foregrounding linguistic alignment in design and evaluation, proposing user-controlled degrees of adaptation and new benchmarks to assess cognitive load and accessibility. The work emphasizes balancing linguistic alignment with respect for linguistic diversity to ensure practical benefits without eroding individual differences in language use.

Abstract

We discuss how desirable it is that Large Language Models (LLMs) be able to adapt or align their language behavior with users who may be diverse in their language use. User diversity may come about among others due to i) age differences; ii) gender characteristics, and/or iii) multilingual experience, and associated differences in language processing and use. We consider potential consequences for usability, communication, and LLM development.