{"slug": "are-llms-becoming-similarly-creative-evidence-from-three-years-of-models", "title": "Are LLMs becoming similarly creative? Evidence from three years of models", "summary": "A new arXiv preprint (2608.19437v1) analyzing three years of LLM releases finds a statistically significant decrease in output diversity on open-ended creative tasks, suggesting models are converging in creative substance. The study, which used sentence-embedding similarity on responses to Infinity-Chat100 and the Alternate Uses Task, warns that this homogenization may diminish human agency in human-AI co-creative work.", "body_md": "arXiv:2608.19437v1 Announce Type: new\nAbstract: Many benchmarks track Large Language Model (LLM) performance on tasks with verifiable answers, but less is known about how LLM performance is evolving on open-ended tasks, where creativity, originality and diversity may matter as much as quality. As LLMs increasingly support human ideation and creative work, understanding trends in LLM performance on open-ended tasks is critical. This paper presents a preliminary analysis of LLM creative outputs spanning three years of model releases, examining model responses to Infinity-Chat100, a real-world collection of open-ended user queries, and the Alternate Uses Task, an established psychometric creativity assessment. Using sentence-embedding similarity, we examine trends in LLM responses to these prompts. Our findings show a statistically significant decrease in model output diversity over time, suggesting that LLM outputs may be converging in creative substance across models. If this trend persists, LLM-driven homogenization may progressively diminish human agency in human-AI co-creative work, demanding careful consideration of LLMs' role in the human creative process.", "url": "https://wpnews.pro/news/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models", "canonical_source": "https://arxiv.org/abs/2608.19437", "published_at": "2026-08-21 04:00:00+00:00", "updated_at": "2026-08-21 04:13:34.065796+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research"], "entities": ["arXiv", "Infinity-Chat100", "Alternate Uses Task"], "alternates": {"html": "https://wpnews.pro/news/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models", "markdown": "https://wpnews.pro/news/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models.md", "text": "https://wpnews.pro/news/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models.txt", "jsonld": "https://wpnews.pro/news/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models.jsonld"}}