{"ID":2867655,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17669","arxiv_id":"2509.17669","title":"PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generation","abstract":"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.","short_abstract":"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) appr...","url_abs":"https://arxiv.org/abs/2509.17669","url_pdf":"https://arxiv.org/pdf/2509.17669v1","authors":"[\"Yan Zhuang\",\"Yuan Sun\"]","published":"2025-09-22T12:12:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}