Search and Filter

SID: Benchmarking Guided Instruction Capabilities in STEM Education with a Socratic Interdisciplinary Dialogues Dataset

Date

AI Overview

Why it matters

Interdisciplinary STEM learning requires expert guidance that is hard to scale, but large language models lack an effective benchmark to evaluate their true capability for guided instruction.

Study at a glance
  • Question: How well do advanced language models guide students through multi-turn, interdisciplinary STEM dialogues?
  • Setting and data: A dataset of 10,000 dialogue turns across 48 complex STEM projects.
  • Method: Benchmark evaluation using a newly created dialogue dataset, pedagogical annotation schema, and evaluation metrics.
Key findings
  • Even state-of-the-art large language models struggle to execute effective guided dialogues.
  • Current models have difficulty leading students to achieve knowledge integration and transfer in complex STEM scenarios.
  • The new benchmark, annotation schema, and evaluation metrics systematically assess the higher-order guidance capabilities of language models.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

Fostering students' abilities for knowledge integration and transfer in complex problem-solving scenarios is a core objective of modern education, and interdisciplinary STEM is a key pathway to achieve this, yet it requires expert guidance that is difficult to scale. While LLMs offer potential in this regard, their true capability for guided instruction remains unclear due to the lack of an effective evaluation benchmark. To address this, we introduce SID, the first benchmark designed to systematically evaluate the higher-order guidance capabilities of LLMs in multi-turn, interdisciplinary Socratic dialogues. Our contributions include a large-scale dataset of 10,000 dialogue turns across 48 complex STEM projects, a novel annotation schema for capturing deep pedagogical features, and a new suite of evaluation metrics (e.g., X-SRG). Baseline experiments confirm that even state-of-the-art LLMs struggle to execute effective guided dialogues that lead students to achieve knowledge integration and transfer. This highlights the critical value of our benchmark in driving the development of more pedagogically-aware LLMs.