본문 바로가기
KERD
논문KCI 등재

문장구역 수업의 보조도구로서의프롬프트 개발에 대한 연구

A Study on Prompt Design as a Scaffolding Tool for Sentence Segmentation Training

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

초록

This study explores the development and application of prompt engineering as a support tool for sentence segmentation training in interpreting education. Focusing on three primary segmentation strategies―segmentation, part-of-speech transformation, and focus shift―the research implemented and compared five types of prompts: zero-shot, few-shot, chain-of-thought (CoT), tree-of-thought (ToT), and graph-of- thought (GoT). The findings suggest that prompts which induce step-by-step reasoning are more effective in enhancing learners’ strategic segmentation skills. Prompt engineering, beyond its technical function, serves as a cognitive scaffolding tool that fosters learners’ metalinguistic awareness and strategic thinking. The study highlights the pedagogical potential of prompt-based AI tools in interpreting and broader higher education contexts.

Abstract

This study explores the development and application of prompt engineering as a support tool for sentence segmentation training in interpreting education. Focusing on three primary segmentation strategies―segmentation, part-of-speech transformation, and focus shift―the research implemented and compared five types of prompts: zero-shot, few-shot, chain-of-thought (CoT), tree-of-thought (ToT), and graph-of- thought (GoT). The findings suggest that prompts which induce step-by-step reasoning are more effective in enhancing learners’ strategic segmentation skills. Prompt engineering, beyond its technical function, serves as a cognitive scaffolding tool that fosters learners’ metalinguistic awareness and strategic thinking. The study highlights the pedagogical potential of prompt-based AI tools in interpreting and broader higher education contexts.

관련 논문AI추천

이 간행물의 다른 논문 (5건)