Challenges & Opportunities

Open challenges with multi-modality; extensions to various subjects; extensions to multiple languages, especially low-resource ones; adaptation to various ages, educational backgrounds and levels; among other topics:

New Strides

  1. Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns (Liu et.al., 2025)
  2. Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment (Favero et.al., 2025)
  3. Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases (Gao et.al., 2025)
  4. Evaluating Multimodal Generative AI with Korean Educational Standards (Park and Kim, 2025)
  5. MM-PhyQA: Multimodal Physics Question-Answering with Multi-image CoT Prompting (Anand et al., 2024)
  6. FineWeb-Edu - the finest collection of educational content the web has to offer (Huggingface, 2024)
  7. Know Your Audience: Do LLMs Adapt to Different Age and Education Levels? (Rooein et al., 2023)

Challenges and Future

  1. "Don't Forget the Teachers": Towards an Educator-Centered Understanding of Harms from Large Language Models in Education (Harvey et.al., CHI 2025)
  2. Foundation Models for Low-Resource Language Education (Vision Paper) (Ding et al., 2024)
  3. Challenges and Opportunities of Moderating Usage of Large Language Models in Education (Krupp et al., 2024)
  4. >
  5. Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges (Li et al., 2024)
  6. Chemvlm: Exploring the power of multimodal large language models in chemistry area (Li et al., 2024)
  7. KidLM: Advancing Language Models for Children – Early Insights and Future Directions (Nayeem and Rafiei, 2024)