UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion

Zhipeng Li, Shuang Zheng, Jiaping Xiao, Xianneng Li, Lei Wang


Abstract
In the field of natural language generation (NLG), controlling text generation (CTG) is critical, particularly in query auto-completion (QAC) where the need for personalization and diversity is paramount. However, it is essentially challenging to adapt to various control objectives and constraints, which results in existing CTG approaches meeting with mixed success. This paper presents UCTG, a unified controllable text generation framework, which introduces a novel prompt learning method for CTG. Specifically, this framework seamlessly integrates a control module, a prompt module, and a generation module. The control module leverages a fine-tuned model to distill user preference features and behavioral patterns from historical data, incorporating human feedback into the model’s loss functions. These features are then transformed by the prompt module into vectors that guide the generation module. As such, the text generation can be flexibly controlled without modifying the task settings. By employing this unified approach, UCTG significantly improves query accuracy and coherence in tasks with different objectives and constraints, which is validated by extensive experiments on the Meituan and AOL real-world datasets. UCTG not only improves text generation control in QAC but also sets a new framework for flexible NLG applications.
Anthology ID:
2025.coling-industry.57
Volume:
Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert, Kareem Darwish, Apoorv Agarwal
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
679–688
Language:
URL:
https://aclanthology.org/2025.coling-industry.57/
DOI:
Bibkey:
Cite (ACL):
Zhipeng Li, Shuang Zheng, Jiaping Xiao, Xianneng Li, and Lei Wang. 2025. UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 679–688, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion (Li et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-industry.57.pdf