Second-language use in dialog … with a GenAI-based chatbot

Teachers and students alike have used or can use GenAI-based chatbots in their first language. They produce texts that at least sound plausible in the commonly taught languages and in some of the less commonly taught languages, if large language models are available. For these languages, GenAI tools can also function as a dialog partner, natural-language search interface, sketch tool, and text adapter to augment CALL pedagogy. For each of these, teachers and students can and should explore their effective use together paying attention to emerging AI literacy (Bowen & Watson, 2024, p. 42ff.) and to considerations of equity and transparency.

• Dialog partner: Starting with a prompt that defines the role and context the GenAI tool is asked to assume or simply with a general question, which will be refined and modified at each turn, students can enter engage in an individual chat in the target language. They can ask for their mistakes to be pointed out and for help with formulations. Tools that have the pedagogic prompts ready for a successful interaction with language learners are increasingly becoming available. In general, teachers should guide these interactions of individual students with the computer, by being available to intervene with help and correction, when necessary.
• Natural-language search interface: Some GenAI tools rely on both a large language model and a powerful search algorithm and index. This allows students to search the internet, using conversational utterances. Searches can be done in the target language and using an iterative approach, modifying the search and correcting the search engine, if the results were not what the students were looking for.
• Sketch tool: Chatbots based on GenAI can be used to generate drafts of passages, lists of ideas, topics, or components, and generally draft documents for brainstorming.
• Text adapter: Texts can be summarized, shortened, or extended. They can be adapted for a different audience or a different proficiency level. Vocabulary lists or lists of specific grammatical construction can be extracted for focused learning.

This blog post is an excerpt from the manuscript for Schulze, Mathias (2025). The impact of artificial intelligence (AI) on CALL pedagogies. In Lee McCallum & Dara Tafazoli (eds) The Palgrave Encyclopedia of Computer-Assisted Language Learning. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-031-51447-0_7-1. 
In 2024, I wrote this encyclopedia entry as my first attempt of gaining a better understanding of what was going on after GenAI burst into Language Education. 

Teachers should set a good example by using GenAI appropriately, also in preparation for their classes and the tests they give to students. This transparency will be the basis for a pedagogically effective and ethical use of these powerful tools by students. The collaborative exploring is necessary to give students the opportunity for reflection and the chance to use GenAI as tools for their language learning and not instead of their language learning.

References

Bowen, J. A., & Watson, C. E. (2024). Teaching with AI. A practical guide to a new era of human learning. John Hopkins University Press.