Research map / Large language models / Agents, code and math
Challenges in the Automatic Analysis of Students’ Diagnostic Reasoning
Claudia Schulz, Christian M. Meyer, Iryna Gurevych
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 |
|---|---|---|---|
| Use Concat rather than the other neural architectures | Epistemic activity identification · MeD | M_A: 23.01 vs. 22.21 and 21.25 | Improved |
| Use Concat rather than the other neural architectures | Epistemic activity identification · TeD | M_A: 21.68 vs. 19.96 and 18.34 | Improved |
| Use Concat rather than Multi-Output | Epistemic activity identification · MeD | hamming loss: 0.07 -> 0.06 | Improved |
| Use Concat rather than Multi-Output | Epistemic activity identification · TeD | hamming loss: 0.07 -> 0.06 | Improved |
| Use Concat rather than Separate | Epistemic activity identification · MeD | M_O EE: 66.43 vs. 66.39 | No clear effect |
| Use a single-label preference baseline that ignores overlaps | BiLSTM-CRF epistemic activity identification · MeD | M_S EE: 75.46 vs. 79.96 | Hurt |
| Use a single-label preference baseline that ignores overlaps | BiLSTM-CRF epistemic activity identification · TeD | M_S EE: 77.21 vs. 78.87 | Hurt |
| Predict overlapping activities jointly rather than only one activity per token | Epistemic activity identification · MeD and TeD | M_O | Mixed |
| Replace neural architectures with the majority baseline | Epistemic activity identification · MeD and TeD | hamming loss: 0.07/0.06 -> 0.11 | Hurt |
| Evaluate with challenge-specific metrics in addition to overall hamming loss | Epistemic activity identification evaluation · MeD and TeD | challenge diagnosis | Improved |
Closest papers by meaning
- AD4CD: Causal-Guided Anomaly Detection for Enhancing Cognitive Diagnosis (AAAI 2025 · similarity 0.85)
- EduDiag: A Benchmark for Educational Diagnostic Reasoning with Error Tracing and Correction on Large Multimodal Models (CVPR 2026 · similarity 0.85)
- Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales (AAAI 2024 · similarity 0.84)
- Knowledge Is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis (AAAI 2025 · similarity 0.83)
- Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems (AAAI 2024 · similarity 0.83)
- Enhancing Cognitive Diagnosis Using Un-interacted Exercises: A Collaboration-Aware Mixed Sampling Approach (AAAI 2024 · similarity 0.83)
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.
