FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation

Zijian Feng, Hanzhang Zhou, Kezhi Mao, Zixiao Zhu


Abstract
Controllable text generation (CTG) seeks to craft texts adhering to specific attributes, traditionally employing learning-based techniques such as training, fine-tuning, or prefix-tuning with attribute-specific datasets. These approaches, while effective, demand extensive computational and data resources. In contrast, some proposed learning-free alternatives circumvent learning but often yield inferior results, exemplifying the fundamental machine learning trade-off between computational expense and model efficacy. To overcome these limitations, we propose FreeCtrl, a learning-free approach that dynamically adjusts the weights of selected feedforward neural network (FFN) vectors to steer the outputs of large language models (LLMs). FreeCtrl hinges on the principle that the weights of different FFN vectors influence the likelihood of different tokens appearing in the output. By identifying and adaptively adjusting the weights of attribute-related FFN vectors, FreeCtrl can control the output likelihood of attribute keywords in the generated content. Extensive experiments on single- and multi-attribute control reveal that the learning-free FreeCtrl outperforms other learning-free and learning-based methods, successfully resolving the dilemma between learning costs and model performance.
Anthology ID:
2024.acl-long.412
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7627–7640
Language:
URL:
https://aclanthology.org/2024.acl-long.412
DOI:
10.18653/v1/2024.acl-long.412
Bibkey:
Cite (ACL):
Zijian Feng, Hanzhang Zhou, Kezhi Mao, and Zixiao Zhu. 2024. FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7627–7640, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation (Feng et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.412.pdf