5 papers
Scalable Generation and Validation of Isomorphic Physics Problems with GenAI
Naiming Liu, Leo Murch, Spencer Moore +4
Traditional synchronous STEM assessments face growing challenges including accessibility barriers, security concerns from resource-sharing platforms, and limited comparability acro…
Using Large Language Models to Assign Partial Credit to Students' Explanations of Problem-Solving Process: Grade at Human Level Accuracy with Grading Confidence Index and Personalized Student-facing Feedback
Zhongzhou Chen, Tong Wan
This study examines the feasibility and potential advantages of using large language models, in particular GPT-4o, to perform partial credit grading of large numbers of student wri…
InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
Yunjia Xi, Jianghao Lin, Menghui Zhu +10
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances…
Using skateboarding to develop a culturally relevant tutorial on static equilibrium
Gian Viray, Isaac Cheney, Tong Wan
Culturally relevant pedagogy (CRP), initially developed by Ladson-Billings, is an instructional framework for supporting diverse learners by drawing on their cultural backgrounds a…
Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
Shuaijiang Zhao, Tingwei Guo, Bajian Xiang +4
The GPT-4o represents a significant milestone in enabling real-time interaction with large language models (LLMs) through speech, its remarkable low latency and high fluency not on…