Talk · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference · October 1, 2026
A Fault-Tolerant Cross-Lingual RAG Architecture for Reliable Curriculum Graph Generation
Altanbek Zulkhazhav, Mamyr Altaibek, Assel Omarbekova, Gulmira Bekmanova
Abstract
Large language models (LLMs) can draft educational programmes quickly, but direct generation is unreliable when the output must satisfy structural constraints such as parseable JSON, acyclic prerequisite relations, semester-order consistency, credit balance, learning-outcome coverage, and recoverability after workflow failures. This paper presents a faulttolerant cross-lingual retrieval-augmented generation (RAG) architecture for reliable curriculum graph generation. The system treats the LLM as a noisy proposal generator rather than a final decision maker. It combines evidence-guided proposal generation with deterministic schema repair, prerequisite-graph validation, semester correction, learning-outcome coverage repair, and persistent task recovery. To evaluate the reliability layer without exposing private institutional data, we build a controlled, seeded curriculum-graph stress-test benchmark with 80 programme intents across eight disciplines, 3,120 courses, 1,197 learning outcomes, 4,765 prerequisite edges, and 3,033 learning-outcome-to-course mappings. Across five random seeds, the proposed pipeline substantially improves structural validity and failure recovery compared with LLM-only and RAG-only variants. It also provides competitive prerequisite-edge recommendation with cycle-free outputs and reduced LLM-call cost. The results do not claim pedagogical optimality; instead, they show that deterministic validation and recoverable execution are necessary control layers for reliable LLM-assisted curriculum graph generation.
More by Altanbek Zulkhazhav
- Quantifying the Intelligibility–Expressivity Tradeoff in Emotion-Conditioned Kazakh Text-to-SpeechInternational Conference on Affective Computing and Intelligent Interaction Workshops and Demos · 2026
- Acoustic and Emotional Annotation of a Web-Harvested Kazakh Speech Corpus for Text-to-Speech2026
- Monitoring and comparative analysis of containerized environmentsFrontiers in Computer Science · 2026
- A Hybrid Attention-LSTM Model with Embedding-based Feature Representation for Student Academic Performance PredictionInternational journal of intelligent engineering and systems · 2026
