Large-scale analysis of wild LLM chat logs finds that user interaction patterns stabilize quickly after initial use and correlate with long-term outcomes like retention, creating an agency paradox of limited exploration in unconstrained systems.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.HC 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Practicing bystander intervention in an LLM multi-agent simulation helps young adults speak up publicly against cyberbullying only after three specific attention shifts from inattention and self-focus to audience awareness and norm-setting.
A three-week group deployment of the ArtKrit drawing tool shows artists evolving from experimentation to selective use within supportive peer networks, suggesting CST evaluations should function as artistic practice opportunities.
citing papers explorer
-
Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild
Large-scale analysis of wild LLM chat logs finds that user interaction patterns stabilize quickly after initial use and correlate with long-term outcomes like retention, creating an agency paradox of limited exploration in unconstrained systems.
-
Attention: What Prevents Young Adults from Speaking Up Against Cyberbullying in an LLM-Powered Social Media Simulation
Practicing bystander intervention in an LLM multi-agent simulation helps young adults speak up publicly against cyberbullying only after three specific attention shifts from inattention and self-focus to audience awareness and norm-setting.
-
Artistic Practice Opportunities in CST Evaluations: A Longitudinal Group Deployment of ArtKrit
A three-week group deployment of the ArtKrit drawing tool shows artists evolving from experimentation to selective use within supportive peer networks, suggesting CST evaluations should function as artistic practice opportunities.