Answers are grounded in this paper and cite their sources.
Groups develop distinctive words even when ordinary expressions are sufficient. Such words can symbolize collective identity, and observational studies link language use to community attachment. We examined identity change in temporary groups of one human and four disclosed large language model (LLM) agents, comparing discussions with and without a neologism proposal across recruitment waves. We recruited 100 Japanese participants in two sequential waves; an agent proposed a new word only in the first wave. Mean collective identity change did not differ significantly between waves. Within the proposal wave, favorable ratings of the proposed word were associated with change in identity, but this association did not survive correction for multiple testing (adjusted $$p=0.229$$ ). The three-way interaction among recruitment wave, message count, and team impression had a nominal $$p=0.027$$ but did not survive correction (adjusted $$p=0.082$$ ). In a sensitivity analysis, the interaction was not significant after adjustment for midpoint identity (nominal $$p=0.078$$ ; adjusted $$p=0.624$$ ). The nonsignificant between-wave comparison and exploratory associations that did not survive correction, together with wave confounding and post-discussion evaluations, limit causal inference and motivate randomized studies with repeated measures to test whether proposed group language affects identification.
No takes yet. Share an insight, caveat, or question.
Ito et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: