Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment

Jianfei Zhang, Jun Bai, Bei Li, Yanmeng Wang, Rumei Li, Chenghua Lin, Wenge Rong


Abstract
Aligning Large Language Models (LLMs) with general human preferences has been proved crucial in improving the interaction quality between LLMs and human. However, human values are inherently diverse among different individuals, making it insufficient to align LLMs solely with general preferences. To address this, personalizing LLMs according to individual feedback emerges as a promising solution. Nonetheless, this approach presents challenges in terms of the efficiency of alignment algorithms. In this work, we introduce a flexible paradigm for individual preference alignment. Our method fundamentally improves efficiency by disentangling preference representation from text generation in LLMs. We validate our approach across multiple text generation tasks and demonstrate that it can produce aligned quality as well as or better than PEFT-based methods, while reducing additional training time for each new individual preference by 80% to 90% in comparison with them.
Anthology ID:
2025.coling-main.323
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4813–4839
Language:
URL:
https://aclanthology.org/2025.coling-main.323/
DOI:
Bibkey:
Cite (ACL):
Jianfei Zhang, Jun Bai, Bei Li, Yanmeng Wang, Rumei Li, Chenghua Lin, and Wenge Rong. 2025. Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4813–4839, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment (Zhang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.323.pdf