Prompt engineering techniques for LLM-based classroom discourse analysis

Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

The article describes a framework of prompting techniques — Vanilla, Chain of Thought, and Self-Ask — applied with zero-shot and few-shot strategies to detect teacher questions from ASR outputs. "Recent advancements have introduced techniques to enhance response quality, such as Chain of Thought (CoT) (Lee et al., 2024) and Self-Ask (SA) (Press et al., 2023)." Self-Ask "explicitly introduces intermediate sub-questions that guide the model through each reasoning step." The framework frames prompt engineering as "designing effective prompts to elicit desired responses from LLMs, crucial for instructing models in specific tasks."

Accounts

• Prompt engineering techniques for LLM-based classroom discourse analysis: The article describes a framework of prompting techniques — Vanilla, Chain of Thought, and Self-Ask — applied with zero-shot and few-shot strategies to detect teacher questions from ASR outputs. "Recent advancements have introduced techniques to enhance response quality, such as Chain of Thought (CoT) (Lee et al., 2024) and Self-Ask (SA) (Press et al., 2023)." Self-Ask "explicitly introduces intermediate sub-questions that guide the model through each reasoning step." The framework frames prompt engineering as "designing effective prompts to elicit desired responses from LLMs, crucial for instructing models in specific tasks." (Lehesvuori et al. (2026))

Claims

• In detecting teacher questions with zero-shot GPT-3.5-turbo, chain-of-thought prompting had slightly higher F1 and precision than Self-Ask but slightly lower recall and balanced accuracy [+M]
• Few-shot chain-of-thought prompting outperforms zero-shot prompting for detecting teacher questions [+M]

Related Research Methods

-

Key Sources

• Lehesvuori, S., Urrutia, F., Heilala, V., Araya, R., & Hämäläinen, R. (2026). Discovering technology-aided possibilities for automatic analysis of science teacher questions. Education Tech Research Dev. https://doi.org/10.1007/s11423-025-10545-3

Page metadata

Field	Value
type	research-method
id	prompt-engineering-techniques-for-llm-based-classroom-discourse-analysis
title	Prompt engineering techniques for LLM-based classroom discourse analysis
description	The article describes a framework of prompting techniques — Vanilla, Chain of Thought, and Self-Ask — applied with zero-shot and few-shot strategies to detect teacher questions from ASR outputs.
status	review
generated	by process:settle-candidates on 2026-10-28
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.