Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild
For system designers of LLM-based chatbots, this work provides empirical evidence of path-dependence in user interactions, highlighting the need to consider early user experiences in design.
This work analyzes 140K chatbot sessions from 7,955 users to show that user-LLM interaction patterns form and stabilize rapidly through early trajectories, with longitudinal outcomes strongly correlated with early exploration, revealing an 'agency paradox' where users explore less despite unconstrained input spaces.
User interactions with LLMs are shaped by prior experiences and individual exploration, but in-lab studies do not provide system designers with visibility into these in-the-wild factors. This work explores a new approach to studying real-world user-LLM interactions through large-scale chat logs from the wild. Through analysis of 140K chatbot sessions from 7,955 anonymized global users over time, we demonstrate key patterns in user expressions despite varied tasks: (1) LLM users are not tabula rasa, nor are they constantly adapting; rather, interaction patterns form and stabilize rapidly through individual early trajectories; (2) Longitudinal outcomes, such as recurring text patterns and retention rates, are strongly correlated with early exploration; (3) Parallel dynamics are present, including organizing expressions by task types such as emotional support, or in response to model-version updates. These results present an ``agency paradox'': despite LLM input spaces being unconstrained and user-driven, we in fact see less user exploration. We call for design consideration surrounding the molding procedure and its incorporation in future research.