A Chinese Abbreviation Prediction Framework Based on Chain-of-Thought Prompting and Semantic Preservation Dynamic Adjustment

Chinese abbreviations improve communicative efficiency by extracting key components from longer expressions. They are widely used in both daily communication and professional domains. However, existing abbreviation generation methods still face two major challenges. First, sequence-labeling-based approaches often neglect contextual meaning by making binary decisions at the character level, leading to abbreviations that fail to capture semantic completeness. Second, generation-based methods rely heavily on a single decoding process, which frequently produces correct abbreviations but ranks them lower due to inadequate semantic evaluation. To address these limitations, we propose a novel two-stage framework with Generation–Iterative Optimization for Abbreviation (GIOA). In the first stage, we design a Chain-of-Thought prompting strategy and incorporate definitional and situational contexts to generate multiple abbreviation candidates. In the second stage, we introduce a Semantic Preservation Dynamic Adjustment mechanism that alternates between character-level importance estimation and semantic restoration to optimize candidate ranking. Experiments on two public benchmark datasets show that our method outperforms existing state-of-the-art approaches, achieving Hit@1 improvements of 15.15% and 13.01%, respectively, while maintaining consistent results in Hit@3.