aiqbench analysis
This research addresses a critical gap in educational AI by replacing opaque LLM decision-making with deterministic modules that explicitly handle pedagogical reasoning. By treating the language model strictly as a linguistic executor, this architecture ensures full traceability and reproducibility of tutoring strategies without relying on expensive commercial infrastructure or GPU clusters. The study demonstrates that upstream orchestration is essential for reliably recovering contextually appropriate content in specialized university courses like dimensional modeling.
A didactical-driven teacher assistant for a dimensional modeling course
arXiv:2607.22598v1 Announce Type: cross Abstract: Educational chatbots powered by large language models (LLMs) show promising effects on learning outcomes, yet most systems delegate pedagogical decisions such as content selection and didactic structuring implicitly to the LLM, making tutoring strategies difficult to trace, evaluate, and reproduce. This paper presents a didactical-driven teacher assistant for a French-language university course on dimensional modelling, operating without commercial LLM budget or GPU infrastructure. The architecture formalises the instructor's pedagogical reasoning into deterministic modules that handle intent detection, concept linking, and didactic approach selection before any text is generated; the LLM acts solely as a linguistic executor. Evaluation on 195 authentic student questions addresses two research questions. First, we show that standard semantic retrieval alone does not reliably recover the pedagogically required content, thereby justifying the upstream orchestration strategy adopted in our architecture (RQ1). Second, compared to free-tier LLMs whose detection performance varies widely across models and which produce errors silently, the deterministic pipeline achieves high pair precision (73%) with full traceability and explicit abstention, though its limited coverage confirms that the detection strategy requires further refinement (RQ2).
Abstract:Educational chatbots powered by large language models (LLMs) show promising effects on learning outcomes, yet most systems delegate pedagogical decisions such as content selection and didactic structuring implicitly to the LLM, making tutoring strategies difficult to trace, evaluate, and reproduce. This paper presents a didactical-driven teacher assistant for a French-language university course on dimensional modelling, operating without commercial LLM budget or GPU infrastructure. The architecture formalises the instructor's pedagogical reasoning into deterministic modules that handle intent detection, concept linking, and didactic approach selection before any text is generated; the LLM acts solely as a linguistic executor. Evaluation on 195 authentic student questions addresses two research questions. First, we show that standard semantic retrieval alone does not reliably recover the pedagogically required content, thereby justifying the upstream orchestration strategy adopted in our architecture (RQ1). Second, compared to free-tier LLMs whose detection performance varies widely across models and which produce errors silently, the deterministic pipeline achieves high pair precision (73%) with full traceability and explicit abstention, though its limited coverage confirms that the detection strategy requires further refinement (RQ2).
Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
arXiv:2607.22598 [cs.CY]
(or arXiv:2607.22598v1 [cs.CY] for this version)
https://doi.org/10.48550/arXiv.2607.22598 Focus to learn more arXiv-issued DOI via DataCite
International Conference on Computer Supported Education, May 2026, Benidorm/Spain, France. pp.177-189
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 287 words
Related coverage
Some Intuitions on Steering Vectors
LessWrong · Sep 29, 2026
Thousand-dimensional structure
AI Alignment Forum · Jul 30, 2026
DreamMimic: Learning Visuomotor Whole-Body Loco-Manipulation via World Model
arXiv · Aug 25, 2026
Frontier post-training recipe review with Finbarr Timbers
Interconnects · Jun 16, 2026