Research map / Probabilistic and scientific modeling / Molecules and proteins
CSG: Cognitive Structure Generation for Intelligent Education
Hengnian Gu, Zhifu Chen, Yuxin Chen, Jin Peng Zhou, Dongdai Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add pretraining on simulated structures to the generic-reward RL variant (ablation) | CSDPM (V3 to V5) · NIPS34 KT | AUC: 0.7196 -> 0.7318 | Improved |
| add pretraining on simulated structures to the generic-reward RL variant (ablation) | CSDPM (V3 to V5) · NIPS34 CD | AUC: 0.7857 -> 0.7997 | Improved |
| add generic-reward RL to the pretrained model (ablation) | CSDPM (V2 to V5) · NIPS34 KT | AUC: 0.6951 -> 0.7318 | Improved |
| add pretraining to the learning-free simulated structures (ablation) | CSDPM (V1 to V2) · NIPS34 KT | AUC: 0.6807 -> 0.6951 | Improved |
| replace generic reward with SOLO hierarchical reward, no pretraining (ablation) | CSDPM (V3 to V4) · NIPS34 KT | AUC: 0.7196 -> 0.7242 | Improved |
| replace generic reward with SOLO hierarchical reward, with pretraining (ablation) | CSG (V5 to CSG) · NIPS34 KT | AUC: 0.7318 -> 0.7413 | Improved |
| replace generic reward with SOLO hierarchical reward, with pretraining (ablation) | CSG (V5 to CSG) · NIPS34 CD | AUC: 0.7997 -> 0.8036 | Improved |
| replace generic reward with SOLO hierarchical reward, with pretraining (ablation) | CSG (V5 to CSG) · ASSISTment17 CD | AUC: 0.7968 -> 0.8003 | Improved |
| use CSG structures instead of GPT-5 generated graphs | downstream KT · FrcSub (500 students) | AUC: 0.7430 -> 0.8602 | Improved |
| use CSG structures instead of Llama-3-70B generated graphs | downstream KT · FrcSub (500 students) | AUC: 0.5170 -> 0.8602 | Improved |
| add Stage II SOLO RL to simulated structures (ablation) | CSG structure quality · FrcSub | Jaccard vs human annotation: 0.46 -> 0.79 | Improved |
| use CSG instead of GPT-5 for structure generation | structure quality · Math2 | Graph edit distance vs human annotation: 0.43 -> 0.21 | Improved |
Closest papers by meaning
- K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs (NeurIPS 2026 · similarity 0.87)
- Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling (NeurIPS 2024 · similarity 0.87)
- Multi-Perspective Consolidation Enhanced Cognitive Diagnosis via Conditional Diffusion Model (AAAI 2025 · similarity 0.86)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.86)
- Generating Computational Cognitive models using Large Language Models (NeurIPS 2025 · similarity 0.85)
- Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
