---
source_url: https://arxiv.org/abs/2605.01097
ingested: 2026-05-13
sha256: 7566914c6c700b93a924eb0db831f656f0e883371f5482259ba8849f8f060b71
---

# Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
arXiv: 2605.01097
Authors: Huang, S., Scarlatos, A., Lee, J., Lan, A.
Published: 2026-05-01
Categories: cs.CL, cs.AI
Venue: arXiv preprint

## Abstract
Existing dialogue-based knowledge tracing (KT) approaches ignore question difficulty modeling and rely on opaque latent representations. We propose an interpretable, difficulty-aware conversational KT framework that integrates Item Response Theory to map LLM outputs into student ability and question difficulty parameters.