Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
By: Yang Liu , Bingjie Yan , Tianyuan Zou and more
Potential Business Impact:
Smaller AI helps big AI learn faster.
Large language models (LLMs) have demonstrated remarkable capabilities, but they require vast amounts of data and computational resources. In contrast, smaller models (SMs), while less powerful, can be more efficient and tailored to specific domains. In this position paper, we argue that taking a collaborative approach, where large and small models work synergistically, can accelerate the adaptation of LLMs to private domains and unlock new potential in AI. We explore various strategies for model collaboration and identify potential challenges and opportunities. Building upon this, we advocate for industry-driven research that prioritizes multi-objective benchmarks on real-world private datasets and applications.
Similar Papers
A Survey on Collaborative Mechanisms Between Large and Small Language Models
Artificial Intelligence
Makes smart AI work on phones and less powerful devices.
Synergistic Weak-Strong Collaboration by Aligning Preferences
Artificial Intelligence
Helps smart computers learn new, specific jobs.
Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges
Distributed, Parallel, and Cluster Computing
Smart computers work together for faster, private AI.