AI tutoring models systematically fail to detect student misconceptions when flawed reasoning coincidentally produces the correct answer, with 71% of failures concentrated in two predictable question types.
TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Personalised education is one of the domains that can greatly benefit from the most recent advances in Artificial Intelligence (AI) and Large Language Models (LLM). However, it is also one of the most challenging applications due to the cognitive complexity of teaching effectively while personalising the learning experience to suit independent learners. We hypothesise that one promising approach to excelling in such demanding use cases is using a \emph{society of minds}. In this chapter, we present TrueReason, an exemplar personalised learning system that integrates a multitude of specialised AI models that can mimic micro skills that are composed together by a LLM to operationalise planning and reasoning. The architecture of the initial prototype is presented while describing two micro skills that have been incorporated in the prototype. The proposed system demonstrates the first step in building sophisticated AI systems that can take up very complex cognitive tasks that are demanded by domains such as education.
fields
cs.CY 2years
2026 2representative citing papers
Real student data shows reasoning models detect 84% of hidden misconceptions versus 57% for fine-tuned classifiers with an 8:1 false positive ratio, motivating a pedagogically grounded pipeline that separates answer correctness from method validity.
citing papers explorer
-
Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning
AI tutoring models systematically fail to detect student misconceptions when flawed reasoning coincidentally produces the correct answer, with 71% of failures concentrated in two predictable question types.
-
The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions
Real student data shows reasoning models detect 84% of hidden misconceptions versus 57% for fine-tuned classifiers with an 8:1 false positive ratio, motivating a pedagogically grounded pipeline that separates answer correctness from method validity.