Participants' prompting was often limited, with poorly formulated prompts leading to vague or unhelpful outputs¶

Claim · All claims
Evidence · 1 study · qualitative r3 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Seven participants explicitly noted in reflective essays that poorly formulated prompts often led to vague, repetitive, or unhelpful outputs, and some attributed unsatisfactory responses to their own input clarity. → Saadet Korucu-Kış 2026

Evidence¶

Saadet Korucu-Kış 2026¶

Saadet Korucu-Kış, Arif Bakla. (2026). Exploring pre-service EFL teachers’ perceptions, use cases and questioning practices of ChatGPT during practicum: a critical digital pedagogy perspective. Instructional Science. https://doi.org/10.1007/s11251-026-09783-6

q2 · i? · qualitative · r3

Thematic analysis of reflective essays and both focus group interviews in the case study. Participants such as İnci complained that without elaboration ChatGPT might give an overly broad answer, and the article notes a growing awareness of the dialogic nature of human–AI interaction.

"Seven participants mentioned this explicitly in their reflective essays, noting that poorly formulated prompts often led to vague, repetitive, or unhelpful outputs."

Discussion¶

Related Claims¶

• More than half of participants' ChatGPT queries sought knowledge or advice, with methodological knowledge and classroom management the largest prompt categories
• Some participants' ChatGPT interactions followed a pattern of inquiry-based learning with iterative prompt refinement
• Students perceive GenAI-assisted translation as challenged by inadequate outputs, limited prompt engineering, and risks to creativity and employment
• Teacher-AI design collaboration faces recurring challenges including prompt literacy, curriculum misalignment, epistemic uncertainty, and explainability barriers
• Students attributed initial passive reliance on GenAI to prompting paralysis and an authority bias compounded by low academic self-efficacy — related
• GenAI novices develop prompting strategies through trial and error, starting from zero-shot prompts and refining them after unsatisfactory outputs — related
• When refined prompts failed, novices overgeneralized and concluded LLMs could not detect anaphors, attributing failure to the model rather than to their prompting — related
• Positive attitudes toward ChatGPT increased from before to during the practicum — related