RL–Based Adaptive Prompt Optimization for User–Centric Structured Sentence Simplification via Small Language Models
Abstract
We introduce a Reinforcement Learning (RL)-based framework to optimize discrete natural language prompts for enhancing both the accuracy and clarity in sentence simplification. Using a lightweight PPO policy, our method learns to guide a frozen small-scale LLaMA-3.2 3B model toward effective simplification for supporting user-centric computational thinking tasks. Results show that our RL-optimized prompts significantly surpass manual baselines in semantic fidelity, logical coherence, and instructional quality. Moreover, the proposed RL-optimized prompting approach enables a much smaller LLM to achieve results that are comparable in clarity and instructional value to those produced by a much larger LLaMA-3.3 70B model.
Fields of Study & Subjects
Text Readability and Simplification
Topic Modeling
Natural Language Processing Techniques
Publication details
- Journal / source
- International Journal of Semantic Computing
- Volume
- 20
- Issue
- 01
- Pages
- 45–69
- Publication date
- 13 February 2026
- Language
- EN