Towards Robust Synthetic Data Generation for Simplification of Text in French
Nikos Tsourakis · Machine Learning and Knowledge Extraction · 2025
We present a pipeline for synthetic simplification of text in French that combines large language models with structured semantic guidance. Our approach enhances data generation by integrating contextual knowledge from Wikipedia and Vikidia articles and injecting symbolic control through lightweight knowledge graphs. To construct document-level representations, we implement a progressive summarization process that incrementally builds running summaries and extracts key ideas. Simplifications are generated iteratively and assessed using semantic comparisons between input and output graphs, enabling targeted regeneration when critical information is lost. Our system is implemented using LangChain’s orchestration framework, allowing modular and extensible coordination of LLM components. Evaluation shows that context-aware prompting and semantic feedback improve simplification quality across successive iterations.