A benchmark dataset pairing 647 human-written STEM lessons with generated, human-reviewed lesson plans across 240 topics, plus a proposed three-part evaluation pipeline.
In: China Conference on Knowledge Graph and Semantic Computing and International Joint Conference on Knowl- edge Graphs, vol
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.CY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LessonBench-V1: A Benchmark Dataset for Evaluating AI Lesson Generation Agents
A benchmark dataset pairing 647 human-written STEM lessons with generated, human-reviewed lesson plans across 240 topics, plus a proposed three-part evaluation pipeline.