文献类型： 会议论文

第一作者： Zijian Feng

作者： Zijian Feng ¹ ; Hanzhang Zhou ¹ ; Zixiao Zhu ¹ ; Kezhi Mao ² ;

作者机构： 1.Institute of Catastrophe Risk Management, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore##Future Resilient Systems Programme, Singapore-ETH Centre, CREATE Campus, Singapore

2.School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore##Future Resilient Systems Programme, Singapore-ETH Centre, CREATE Campus, Singapore

会议名称： [ "Annual Meeting of the Association for Computational Linguistics" , "Annual meeting of the Association for Computational Linguistics"]

主办单位：

页码： 7627-7640

摘要： 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.

分类号： tp391