{"slug": "disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing", "title": "Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing", "summary": "Researchers propose Phase-Aware Knowledge Tracing (PAKT), a framework that decomposes student learning interactions into ability and proficiency phases to improve knowledge tracing. PAKT uses a multi-branch Transformer with a type-aware readout module to capture phase-specific and holistic knowledge states, achieving up to 1.33% AUC improvement over baselines on six benchmarks.", "body_md": "arXiv:2607.13103v1 Announce Type: new\nAbstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing KT methods usually treat the raw interaction sequence as a unified behavioral process, overlooking the phase-specific nature of learning behaviors. Our preliminary observations show that students are more likely to correctly answer previously failed knowledge concepts after sufficient practice, suggesting a transition from ability-building to proficiency-oriented learning. Motivated by this, we propose Phase-Aware Knowledge Tracing (PAKT), a KT framework that decomposes student interactions into ability and proficiency phases based on the tailored decomposition mechanism. To effectively exploit the decomposed sequences, we design a multi-branch Transformer with a type-aware readout module to jointly capture phase-specific and holistic knowledge states. We further provide a causal analysis to reveal the confounding bias caused by entangling complex learning behaviors in phase-agnostic KT models. Extensive experiments on six public benchmarks demonstrate that our method consistently outperforms representative baselines, with a maximum AUC gain of 1.33% and an average gain of 0.82%.", "url": "https://wpnews.pro/news/disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing", "canonical_source": "https://arxiv.org/abs/2607.13103", "published_at": "2026-07-16 04:00:00+00:00", "updated_at": "2026-07-16 04:29:08.454394+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing", "markdown": "https://wpnews.pro/news/disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing.md", "text": "https://wpnews.pro/news/disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing.txt", "jsonld": "https://wpnews.pro/news/disentangling-knowledge-states-with-ability-and-proficiency-modeling-for-tracing.jsonld"}}