LLM simulators exhibit near-zero selective response to targeted misconception feedback and behave sycophantically, but SFT and SFS-aligned RL improve this property.
Deep knowledge tracing.Advances in neural information processing systems, 28, 2015
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Re-evaluation under controlled protocols shows that attention-enhanced PKT models do not consistently outperform standard DKT on the CodeWorkout dataset.
LiveGraph improves exercise recommendations by using graph representations to link student histories and dynamic re-ranking to boost both accuracy and content diversity on real-world learning datasets.
citing papers explorer
-
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
LLM simulators exhibit near-zero selective response to targeted misconception feedback and behave sycophantically, but SFT and SFS-aligned RL improve this property.
-
Ensuring Reliability in Programming Knowledge Tracing: A Re-evaluation of Attention-augmented Models and Experimental Protocols
Re-evaluation under controlled protocols shows that attention-enhanced PKT models do not consistently outperform standard DKT on the CodeWorkout dataset.
-
LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation
LiveGraph improves exercise recommendations by using graph representations to link student histories and dynamic re-ranking to boost both accuracy and content diversity on real-world learning datasets.