AIEDHK
← 연구 뉴스로 돌아가기

#preprint

preprint

10 논문

Illustrative photograph of a teacher-education group discussing a short fictional tutoring exchange, with two alternative response cards on a seminar table.
도구 / 데이터셋2026
도구 / 데이터셋 249

Preprint: TutorCaseBench separates recognizing a strategy from responding to a learner

Yeon Su Park, Chanyoung Park, Tae Soo Kim, Seungju Kim, Hyunwoo Kim, Daho Jung, Jinsung Yoon, Juho Kim

arXiv preprint

A benchmark builds simulated tutoring cases from qualitative education studies. Models were more successful at choosing a proposed strategy than at generating a response adapted to the particular situation.

preprintAI tutor evaluationcase-based assessment
500단어 요약 읽기 →
Illustrative photograph of two educators examining a simple prediction baseline and uneven error bars on a seminar-room display.
도구 / 데이터셋2026
도구 / 데이터셋 245

Preprint: Tutoring logs add little to simple score predictions in one course

Zeyu Dong, Mikael Kwame Kuada, Asa Holley Buchakjian-Tweedy, Ibrahem Aljabea

arXiv preprint

A retrospective analysis compares tutoring-interaction features with constant score predictions. Small overall gains and uneven errors show why a support model needs more than a favorable average accuracy figure.

preprintlearning analyticsprediction baselines
500단어 요약 읽기 →
Illustrative research-review scene with two raters comparing repeated and progressive activity sequences beside a screen with one rising and one falling chart.
도구 / 데이터셋2026
도구 / 데이터셋 239

Preprint: Raising a tutor metric lowered human ratings in an optimization experiment

Daniel Domínguez Figaredo, Rafael Fernández De la Cruz

arXiv preprint

An optimization experiment produced higher automated scores but lower human ratings for instructional sequences. Its synthetic cases and constrained intervention make it a warning about evaluation design, not evidence of harm to actual students.

preprintAI tutoringevaluation validity
500단어 요약 읽기 →
밝은 분위기의 평가 상담실에서 흑인 강사와 남아시아 출신 대학생이 주석이 달린 프로그래밍 답안, 분기 다이어그램, 그리고 서로 겹쳐진 채점 기준표 항목들을 함께 살펴보고 있다.
도구 / 데이터셋2026
도구 / 데이터셋 228

프리프린트: 세분화된 AI 채점 기준이 서로 다른 학습 문제를 반드시 진단하는 것은 아니다

Xi Zhao, Xinyue Jiao, Zhen Xu

arXiv preprint

컴퓨터 과학 답안 3,041개를 분석한 한 사전 공개 논문에 따르면, AI가 제시한 상세 채점 항목들은 서로 강하게 중첩되는 경향을 보였으며, AI가 제공한 피드백에서 발견된 오개념의 수는 강사가 직접 남긴 의견보다 적었다. 이 연구는 "평가 도구가 단순히 그럴듯한 점수를 산출하는 것을 넘어, 학습자가 범한 오류의 원인을 제대로 설명해 줄 수 있는가?"라는 실질적인 질문을 던진다.

사전 공개 논문자동화된 평가컴퓨터 과학 교육
500단어 요약 읽기 →
An East Asian female university student and a South Asian male language tutor compare bilingual economics notes and two AI explanations in a sunlit campus language centre
도구 / 데이터셋2026
도구 / 데이터셋 226

Preprint: Students’ access to generative AI did not ensure equally usable support across languages

Ming Li, Qin Xie, Ariunaa Enkhtur, Lilan Chen, Fei Cheng

arXiv preprint (work in progress)

Interviews with 42 undergraduates at universities in China, Japan, and Mongolia explored how students selected AI tools, chose interaction languages, and checked outputs. Participants described different routes from technical access to useful academic support, including switching languages when responses seemed inadequate. This work-in-progress preprint presents situated accounts rather than national comparisons or measured learning gains. It raises practical questions about evaluating an AI service in the languages students actually use.

preprintmultilingual educationAI access
500단어 요약 읽기 →
A Black female university student listens through headphones and uses a physical playback control while a White male accessibility specialist reviews a graph and lecture monitor nearby
도구 / 데이터셋2026
도구 / 데이터셋 224

Preprint: Lecture audio-description rules and listener preferences did not always agree

Stylianos Psychias, Yingqiang Gao

arXiv preprint

AD4Edu proposes a benchmark and evaluation framework for describing visual information in university lectures. Four blind or low-vision raters assessed 400 description pairs, revealing a gap between compliance with the researchers’ rules and individual preferences, especially about length. This preprint offers tools for studying that gap, with small-sample and playback limitations. It does not demonstrate improved course learning or certify that a lecture meets accessibility requirements.

preprintaccessibilityaudio description
500단어 요약 읽기 →
Illustrative scene of a learner and tutor comparing a handwritten triangle solution with a laptop showing a triangle and branching hint paths at an evening study desk.
도구 / 데이터셋2026
도구 / 데이터셋 235

Preprint: Adaptive tutor prompts changed interaction patterns without establishing better learning

Po-Chin Chang, Nicholas Hogan, Aske Plaat, Michiel T. van der Meer

arXiv preprint, version 1

A high-school tutoring preprint examines adaptive prompt selection. Its interaction results invite closer study, but limited exercise data and nonsignificant outcome comparisons leave the learning advantage unresolved.

preprintadaptive tutoringprompt selection
500단어 요약 읽기 →