paper
Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
paperactiveprovisional
detecting-knowledge-gaps-from-conversational-ai-interactions-using-curriculum-prerequisite-graphs-b4c42c1a·1 events·first seen 7d agoAliases: Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
Co-occurring entities
More like this (12)
Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generationknowledge graph promptingArtificial Analysis Conversational DynamicsEfficient ASR Training with Conversations that Never HappenedUnsupervised Continual Clustering via Forward-Backward Knowledge DistillationProvenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data CurationResearch Gap Inferencetemporal knowledge graphGenerative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature InteractionsGenerative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature InteractionsExpert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Modelsknowledge graph
Recent events (1)
Pipeline detects curriculum knowledge gaps from student-AI conversational logs using prerequisite graphs
Researchers present a pipeline that classifies student questions directed at a conversational AI teaching assistant into curriculum topics using a few-shot classifier grounded in a GPT-4-extracted prerequisite knowledge graph. Evaluated on 1,340 questions from 164 graduate students, the classifier achieves 80% accuracy across 43 labels. Topic-level question volume significantly correlates with student-reported difficulty (rho=0.491), validating that AI interaction logs carry actionable diagnostic signals about knowledge gaps.