Benchmark

CogBench Benchmarking Cognitive Alignment of Large Language Models in Educational Question Answering

We propose an LLM-driven automated framework to build large-scale multimodal educational knowledge graphs from open courses, achieving robust cross-modal alignment and …

avatar
Tong Lu

CogBench: Benchmarking Cognitive Alignment of Large Language Models in Educational Question Answering

Large language models (LLMs) possess strong capabilities in language understanding and generation, as well as remarkable problem-solving abilities. In the educational domain, a …

avatar
Tong Lu