Exploring how EFL students talk to and through AI to develop texts

• URL: http://arxiv.org/abs/2605.12523v1
• Date: Mon, 06 Apr 2026 04:51:05 GMT
• Title: Exploring how EFL students talk to and through AI to develop texts
• Abstract summary: Generative Artificial Intelligence (AI) introduces new considerations for English as a foreign language (EFL) writing.<n>This study explores how students talk to and through AI by prompt engineering and negotiating.
• Score: 15.134980087210025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Artificial Intelligence (AI) introduces new considerations for English as a foreign language (EFL) writing pedagogy. This study explores how students talk to and through AI by prompt engineering and negotiating authorship, respectively, and whether any patterns in the latter relate to students' writing performance. Using an exploratory mixed methods design, we analyzed screen recordings of 44 Hong Kong secondary students completing a Curricular Writing Task with AI Chatbots. Content analysis identified ten types of prompting strategies students employed, including questions, searches, and detailed instructions. From clustering these strategies, three distinct profiles of human-AI rhetorical load responsibility emerged: AI-dominant (52% of students), Human-dominant (25%) and Collaborative human-AI (14%). A MANOVA analysis indicated no significant multivariate effect of rhetorical load responsibility on three dimensions of students' writing performance: content, language, and organization. Students' prompting strategies and rhetorical load responsibility patterns have implications for their engagement and autonomy in EFL writing pedagogy.

Related papers

• "How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations [39.146761527401424]
  This paper focuses on such student questions from two datasets of distinct learning contexts: formative self-study, and summative assessed coursework.<n>We analysed 6,113 messages from both learning contexts using 11 different Large Language Models (LLM) and three human raters.<n>Results show that 'procedural' questions predominated in both learning contexts, but more so when students prepare for summative assessment.
  arXiv  Detail & Related papers  (2026-02-20T17:27:41Z)
• Writing With Machines and Peers: Designing for Critical Engagement with Generative AI [5.719812010814006]
  This study proposes a pedagogical design that integrates AI and peer feedback in a graduate-level academic writing activity.<n>Students developed literature review projects through multiple writing and revision stages, receiving feedback from both a custom-built AI reviewer and human peers.
  arXiv  Detail & Related papers  (2025-11-19T02:17:42Z)
• One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning [39.357397697061664]
  We propose a novel approach to generating personalized English reading comprehension tests tailored to students' interests.<n>We generate new passages and multiple-choice reading comprehension questions that are linguistically similar to the original passages but semantically aligned with individual learners' interests.<n>Our results show students learning with personalized reading passages demonstrate improved comprehension and motivation retention compared to those learning with non-personalized materials.
  arXiv  Detail & Related papers  (2025-11-12T09:17:25Z)
• A vibe coding learning design to enhance EFL students' talking to, through, and about AI [5.671810777243196]
  This article reports on the piloting of vibe coding (using natural language to create software applications with AI) for English as a Foreign Language education.<n>We developed a human-AI meta-languaging framework with three dimensions: talking to AI (prompt engineering), talking through AI (negotiating authorship), and talking about AI.
  arXiv  Detail & Related papers  (2025-09-09T00:27:04Z)
• Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues [48.99818550820575]
  Recent studies have shown that strategies used by tutors can have significant effects on student outcomes.<n>Few works have studied predicting tutor strategy in dialogues.<n>We investigate the ability of modern LLMs, particularly Llama 3 and GPT-4o, to predict both future tutor moves and student outcomes in dialogues.
  arXiv  Detail & Related papers  (2025-07-09T14:47:35Z)
• The Agency Gap: How Generative AI Literacy Shapes Independent Writing after AI Support [4.013708138746962]
  This study investigates the extent to which GenAI literacy predicts student writing performance in contexts that require self-initiation and regulation.<n>Writing was evaluated across insightfulness, visual data integration, organisation, linguistic quality, and critical thinking.
  arXiv  Detail & Related papers  (2025-07-06T14:01:06Z)
• Exploring EFL Secondary Students' AI-generated Text Editing While Composition Writing [2.8109476541924234]
  Generative Artificial Intelligence is transforming how English as a foreign language students write.<n>This study investigates how students integrate and modify AI-generated text when completing an expository writing task.
  arXiv  Detail & Related papers  (2025-05-13T03:46:00Z)
• Approaching the Limits to EFL Writing Enhancement with AI-generated Text and Diverse Learners [3.2668433085737036]
  Students can compose texts by integrating their own words with AI-generated text.<n>This study investigated how 59 Hong Kong secondary school students interacted with AI-generated text to compose a feature article.
  arXiv  Detail & Related papers  (2025-03-01T06:29:00Z)
• Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs [50.0874045899661]
  We introduce CharacterBot, a model designed to replicate both the linguistic patterns and distinctive thought patterns as manifested in the textual works of a character.<n>Using Lu Xun, a renowned Chinese writer as a case study, we propose four training tasks derived from his 17 essay collections.<n>These include a pre-training task focused on mastering external linguistic structures and knowledge, as well as three fine-tuning tasks.<n>We evaluate CharacterBot on three tasks for linguistic accuracy and opinion comprehension, demonstrating that it significantly outperforms the baselines on our adapted metrics.
  arXiv  Detail & Related papers  (2025-02-18T16:11:54Z)
• Effects of a Prompt Engineering Intervention on Undergraduate Students' AI Self-Efficacy, AI Knowledge and Prompt Engineering Ability: A Mixed Methods Study [36.48421439947282]
  This study designed and implemented a prompt engineering intervention at a university in Hong Kong. It examined students' AI self-efficacy, AI knowledge, and proficiency in creating effective prompts.
  arXiv  Detail & Related papers  (2024-07-30T15:05:24Z)
• Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students [35.05435052195561]
  The increasing use of Artificial Intelligence (AI) by students in learning presents new challenges for assessing their learning outcomes. This paper introduces a co-design study to explore the potential of students' AI usage data as a novel material for assessment.
  arXiv  Detail & Related papers  (2024-01-26T14:49:29Z)
• EFL Students' Attitudes and Contradictions in a Machine-in-the-loop Activity System [5.326832235832844]
  This study investigates the attitudes and contradictions of 67 English as a foreign language (EFL) students towards machine-in-the-loop writing. Results revealed mostly positive attitudes, with some negative or mixed feelings.
  arXiv  Detail & Related papers  (2023-07-13T07:38:11Z)
• Exploring User Perspectives on ChatGPT: Applications, Perceptions, and Implications for AI-Integrated Education [40.38809129759498]
  ChatGPT is most commonly used in the domains of higher education, K-12 education, and practical skills training. On one hand, some users view it as a transformative tool capable of amplifying student self-efficacy and learning motivation. On the other hand, there is a degree of apprehension among concerned users.
  arXiv  Detail & Related papers  (2023-05-22T15:13:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.