Article

Calibrating Gemini to Human Raters in Spoken Language Assessment for EFL Learners in Asia

2026-08-07

Abstract excerpt

<title>Abstract</title> <p>Generative AI assessment research often focuses on ChatGPT and written language. The current study investigated the viability of calibrating Gemini 2.5 Flash with human ratings for assessing L2 English speech. Dialogue audio files were utilised in zero-shot, 5-shot, and 10-shot prompting conditions across 11 rating scales. Gemini’s ratings were compared with two sets of human-rater pair...

Topics

Open a Topic to create a Post that cites this publication.

COVID-19 diagnosis using AI

Identifiers and source

Literature Corpus work: e5b69a1f-e901-569f-a1f1-e674f4b7cbc5
DOI: 10.21203/rs.3.rs-10575517/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Calibrating Gemini to Human Raters in Spoken Language Assessment for EFL Learners in AsiaDOI 10.21203/rs.3.rs-10575517/v1Read

Human and LLM accent rating of English-L2 speech by Brazilian speakersSemantic proximity Read

Assessing additional language oral production with ChatGPT: Validity, differences, and agreement with human ratersSemantic proximity Read

A Narrative Review of ChatGPT in Education: The Benefits and ChallengesSemantic proximity Read

Finding the Human Voice in AI: Insights on the Perception of AI-Voice Clones from Naturalness and Similarity RatingsSemantic proximity Read

Can AI replace Teachers? Comparing AI and Human Teachers’ ratings and feedback on students’ essaysSemantic proximity Read

Beyond Automated Scoring: An Evidence-Informed Human–GenAI Complementarity Framework for Formative Writing AssessmentSemantic proximity Read

Can ChatGPT Replace the Teacher in Assessment? A Review of Research on the Use of Large Language Models in Grading and Providing FeedbackSemantic proximity Read

Passing the Turing Test: Fine-tuned AI feedback is less detectable than human or prompt-engineered feedbackSemantic proximity Read

ChatGPT vs. Bard: A Comparative StudySemantic proximity Read

A Comparative Study of Cultural Hallucination in Large Language Models on Culturally Specific Ethical QuestionsSemantic proximity Read

Culturally-Aware Prompting in Conversational AI: Enhancing Digital Inclusion and Sustainable Collaboration for Cross-cultural Teams in AustraliaSemantic proximity Read

A Systematic Comparative Review of Generative AI vs. Teacher Feedback in EFL Writing: Learner Perceptions, Preferences, and Psychological FactorsSemantic proximity Read