{"slug": "adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild", "title": "Adopt $\\neq$ Adapt: Longitudinal Analyses of LLM Conversations in the Wild", "summary": "A longitudinal analysis of approximately 12,000 Microsoft Bing Copilot users found that individual user habits remain overwhelmingly sticky over time, with weak trends in personal conversational trajectories despite significant population-level shifts. More active users engaged in longer, more successful conversations and used the LLM for complex, professional tasks, while comparisons with the WildChat-4.8M dataset revealed that it is skewed toward highly proficient \"power\" users and does not represent typical user-AI interactions. The findings demonstrate that existing user behavior is difficult to change and highlight significant user heterogeneity, cautioning against overgeneralizing from skewed datasets.", "body_md": "arXiv:2605.29018v1 Announce Type: new\nAbstract: Although a growing body of research has begun to describe user--LLM interactions, the picture it paints is largely static; little is known about how individual users change their behavior over time. To address this gap, we analyze the conversational trajectories of $\\sim$12,000 randomly sampled Microsoft Bing Copilot users and compare these with data from WildChat-4.8M. While the Copilot data contains significant population-level trends, we find that trends in individual user trajectories are much weaker; user habits prove to be overwhelmingly sticky. We also find stark differences between users of different activity levels: more active users have more successful conversations and use the LLM for more complex and professionally oriented tasks. Some user trends also appear in WildChat-4.8M, but we find evidence that this dataset is significantly skewed towards highly proficient \"power\" users. Ultimately, our results suggest that existing user behavior is difficult to change and demonstrate the extent of user heterogeneity. Our comparison between datasets highlights that WildChat does not represent typical user-AI interactions, an important caveat for downstream uses of the data.", "url": "https://wpnews.pro/news/adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild", "canonical_source": "https://arxiv.org/abs/2605.29018", "published_at": "2026-05-29 04:00:00+00:00", "updated_at": "2026-05-29 04:21:09.062574+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research", "ai-products"], "entities": ["Microsoft Bing Copilot", "WildChat-4.8M", "WildChat"], "alternates": {"html": "https://wpnews.pro/news/adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild", "markdown": "https://wpnews.pro/news/adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild.md", "text": "https://wpnews.pro/news/adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild.txt", "jsonld": "https://wpnews.pro/news/adopt-neq-adapt-longitudinal-analyses-of-llm-conversations-in-the-wild.jsonld"}}