3 papers
cs.CY2026
A Multi-Agent Approach to Validate and Refine LLM-Generated Personalized Math Problems
Fareya Ikram, Nischal Ashok Kumar, Junyang Lu +4
Students benefit from math problems contextualized to their interests. Large language models (LLMs) offer promise for efficient personalization at scale. However, LLM-generated per…
cs.CL2025
DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images
Sami Baral, Li Lucy, Ryan Knight +4
In real-world settings, vision language models (VLMs) should robustly handle naturalistic, noisy visual content as well as domain-specific language and concepts. For example, K-12…
cs.CY2024
Automated Feedback in Math Education: A Comparative Analysis of LLMs for Open-Ended Responses
Sami Baral, Eamon Worden, Wen-Chiang Lim +4
The effectiveness of feedback in enhancing learning outcomes is well documented within Educational Data Mining (EDM). Various prior research has explored methodologies to enhance t…