Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
This is an incremental position paper proposing collaboration strategies for domain-specific AI applications.
This position paper argues that collaborative approaches between large and small models can accelerate LLM adaptation to private domains and unlock new AI potential, exploring strategies and advocating for industry-driven research on multi-objective benchmarks.
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.