From Written Response to Dialogue with AI: How Activity Format, Interaction Modality, and Language Impact Student Learning and Engagement

2026-10-05

AI Summary

This study addresses the vulnerability of written assignments to AI-generated ghostwriting in the era of large language models by investigating the efficacy of AI conversational learning in multilingual settings. Through a field experiment involving 305 students, it systematically compares learning outcomes across written, text-based, and voice-mediated AI dialogues under varying language configurations. The work proposes novel design paradigms incorporating mixed-modality control and native-language scaffolding, revealing the distinct advantages of bilingual voice interaction. Results indicate that conversational activities significantly enhance learning interest and self-efficacy. Furthermore, bilingual voice interaction effectively reduces attrition rates and increases comprehension-oriented dialogue turns, although no significant differences are observed in knowledge gains.

Abstract

The widespread availability of LLMs is challenging written learning activities, as students can increasingly generate responses without necessarily engaging with the learning content. Conversational AI creates an opportunity to redesign these activities as dialogue, while multilingual capabilities may make such dialogue more accessible to students learning through a non-native language. We conducted a field study with 305 native Kannada-speaking undergraduate students at English-medium institutions in Karnataka, India. We compared written response activities with text- and voice-based dialogic activities with AI, each conducted in English-only or bilingual Kannada-English settings. Students who completed dialogic activities spent more time on the activities, contributed more, and reported greater interest and self-efficacy than those completing written responses, although fewer students completed the dialogic activities overall. Knowledge increased across all conditions, with no reliable differences in gains between activity formats or languages. Language shaped participation differently across modalities: bilingual interaction was particularly beneficial in voice dialogue, where it reduced articulation difficulties, increased turns demonstrating understanding, and reduced conversation abandonment. However, students also valued English because of its connection to their academic and professional aspirations. These findings show that designing dialogic learning with AI requires more than choosing between writing and dialogue, voice and text, or English and students' native languages. We highlight opportunities to give learners greater control over modality, information, and pace, and to use native languages as translanguaging support rather than as a replacement for English.

Problem

• AI dialogue
• student engagement
• interaction modality
• multilingual learning
• large language models

Innovation

• Conversational AI
• Dialogic Learning
• Multimodal Interaction
• Translanguaging
• Bilingual Education