Let’s Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification
Year: 2026
Type: conference-paper
Abstract: Large language models demonstrate limited capability in proficiency-controlled sentence simplification, particularly when simplifying across large readability levels.We propose a framework that decomposes complex simplifications into manageable steps through dynamic path planning, semantic-aware exemplar selection, and chain-of-thought generation with conversation history for coherent reasoning.Evaluation on five languages across two benchmarks shows our approach improves simplification effectiveness while reducing computational steps by 22-42%.Human evaluation confirms the fundamental trade-off between simplification effectiveness and meaning preservation.Notably, even human annotators struggle to agree on semantic preservation judgments, highlighting the inherent complexity of this task.Our work shows that while step-by-step simplification improves control, preserving semantic fidelity during extensive simplification remains an open challenge.
Institutions: Tianjin University, Guangdong University of Foreign Studies
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140095404