Learning Through Dialogue: Engagement and Efficacy Matter More Than Explanations

TL;DR

This study investigates how linguistic features and interaction dynamics in human-LLM conversations influence learning outcomes, emphasizing that engagement and confidence are more affected by interaction quality than explanations alone.

Contribution

It reveals that LLM explanations support confidence through reflection and knowledge through engagement, with effects varying by user political efficacy and interaction length.

Findings

Explanatory richness boosts confidence via reflection.

Knowledge gain depends on user engagement and conversation length.

Effects are highly conditional on user political efficacy.

Abstract

Large language models (LLMs) are increasingly used as conversational partners for learning, yet the interactional dynamics supporting users' learning and engagement are understudied. We analyze the linguistic and interactional features from both LLM and participant chats across 397 human-LLM conversations about socio-political issues to identify the mechanisms and conditions under which LLM explanations shape changes in political knowledge and confidence. Mediation analyses reveal that LLM explanatory richness partially supports confidence by fostering users' reflective insight, whereas its effect on knowledge gain operates entirely through users' cognitive engagement. Moderation analyses show that these effects are highly conditional and vary by political efficacy. Confidence gains depend on how high-efficacy users experience and resolve uncertainty. Knowledge gains depend on high-efficacy users' ability to leverage extended interaction, with longer conversations benefiting primarily reflective users. In summary, we find that learning from LLMs is an interactional achievement, not a uniform outcome of better explanations. The findings underscore the importance of aligning LLM explanatory behavior with users' engagement states to support effective learning in designing Human-AI interactive systems.