Tencent’s new AI method aligns preferences without retraining
Researchers have developed a new method for aligning large language models with multiple user preferences at once, improving performance without requiring retraining.
Harbin Institute of Technology, Shenzhen, China; Nanyang Technological University, Singapore; Peng Cheng Laboratory, China; Beijing Academy of Artificial Intelligence, China; Tencent, China
Authors: Zhuo Li et al.
The study presents a framework called Hierarchical Mixture-of-Experts (HoE), which aligns large language models (LLMs) with diverse user preferences without substantial retraining. This is notable, as traditional methods often have difficulty balancing multiple objectives and typically require costly adjustments.
This research questions the common assumption that models must be retrained to handle different tasks or objectives. The HoE framework provides a more flexible and cost-efficient alternative, with potential applications in real-world settings like personalized digital assistants that must adapt to changing user needs without ongoing retraining.
The approach depends on access top pre-trained single-objective models, which may not always be available. Its performance also varies based on the effectiveness of the model merging techniques applied.
The HoE framework offers a new approach to align AI models with user preferences, providing a more adaptable and efficient method for handling diverse tasks.
Read full article on Tech in Asia
Technology
Comments
Leave a comment in Nestia App