← Back to all news
arXiv Computation and Language By Chen Cecilia Liu, Roi Reichart, Anna Korhonen

Cultural Adaptation within Repeated Social Interactions

Read the original on arXiv Computation and Language →

The paper explores how large language models (LLMs) can adapt culturally through repeated social interactions in a sandbox setting. It reframes cultural adaptation as a continuous norm‑assimilation process, showing that memory mechanisms enable longitudinal learning, transfer across different social contexts, and multilingual norm assimilation in five languages. These results establish a foundation for interaction‑driven cultural adaptation in LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 16

LLMs Infer Cultural Context but Fail to Apply It When Responding

The paper introduces CAPRI, a dataset of conversations designed to test whether large language models (LLMs) can adapt their responses to users’ cultural backgrounds. Experiments show that while LLMs can infer a user’s cultural context and recall relevant conventions, they frequently fail to apply this knowledge when generating answers unless explicitly prompted to do so. The study also finds that LLMs’ cultural adaptations improve as more cues are provided, yet their default priors are not culture‑neutral and sometimes reflect the model’s country of origin.

By Yisong Miao, Jian Zhu, Vered Shwartz
llmsbenchmarks
More like this →