PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generation
This work addresses controllable text generation for enhancing reliability and user experience in LLM applications, representing an incremental advancement over traditional methods.
The paper tackles the problem of controllable text generation by proposing PG-CE, a method that decomposes tasks into type prediction, constraint construction, and guided generation, resulting in significant improvements in generation quality across multiple scenarios while maintaining controllability and relevance.
With the rapid development of Large Language Models (LLMs), Controllable Text Generation (CTG) has become a critical technology for enhancing system reliability and user experience. Addressing the limitations of traditional methods, this paper proposes the PG-CE (Progressive Generation with Constraint Enhancement) approach, which decomposes CTG tasks into three steps: type prediction, constraint construction, and guided generation. This method employs constraint generation models to dynamically build multi-dimensional constraints including tone, expression style, and thematic focus to guide output. Experiments demonstrate that PG-CE significantly improves generation quality across multiple scenarios while maintaining text controllability, thematic relevance, and response practicality. The research developed a dataset containing 90,000 constraint-text pairs (with an 8:2 ratio between daily and other topics), effectively reflecting real-world application requirements.