Curiosity as Linguistic Intervention: Using LLM Tutoring Dialogues to Influence Exploratory Learning Behavior
For researchers in AI tutoring and cognitive science, this work provides a scalable method to study and enhance exploratory learning through LLM-mediated dialogue, though the gains are specific to conversational turn count and may not generalize to deeper learning outcomes.
The paper introduces CURIOBOT, a framework using LLM tutoring dialogues to influence exploratory learning behavior via linguistic interventions based on Berlyne's collative variables. Across 270 conversations, curiosity-oriented interventions increased exploratory learner behaviors by up to 2.4x more conversational turns under fixed time budgets.
Large Language Models (LLMs) provide a new opportunity to study how language shapes exploratory cognition because conversational strategies can be systematically manipulated at inference time. We introduce CURIOBOT, a framework that operationalizes Berlyne's collative variables, novelty, complexity, conflict, and uncertainty, as adaptive linguistic interventions for conversational tutoring. Across 270 tutoring conversations spanning multiple model families, domains, and topic complexity levels, curiosity-oriented interventions consistently increased exploratory learner behaviors, producing up to 2.4x more conversational turns under fixed time budgets. To measure these effects, we further introduce a learner-centered evaluation framework capturing exploratory questioning, conversational agency, productive struggle, and observable curiosity. Learner-side gains persisted even when tutor-side instructional quality remained unchanged, suggesting that curiosity functions as a partially independent interaction-level mechanism. More broadly, our results demonstrate that LLM-mediated dialogue can serve as a scalable experimental framework for studying how language shapes exploratory learning behavior.