A Survey on Collaborative Mechanisms Between Large and Small Language Models

TL;DR

This survey reviews mechanisms for collaboration between large and small language models, highlighting their potential to enable efficient, privacy-preserving, and adaptable AI applications on resource-constrained devices.

Contribution

It provides a comprehensive overview of interaction mechanisms, enabling technologies, and application scenarios for LLM-SLM collaboration, and discusses future research directions and challenges.

Findings

Collaboration mechanisms include pipeline, routing, auxiliary, distillation, fusion.

LLM-SLM collaboration enhances AI efficiency, privacy, and personalization.

Challenges include system overhead, consistency, security, and evaluation complexity.

Abstract

Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance. Collaboration between LLMs and SLMs emerges as a crucial paradigm to synergistically balance these trade-offs, enabling advanced AI applications, especially on resource-constrained edge devices. This survey provides a comprehensive overview of LLM-SLM collaboration, detailing various interaction mechanisms (pipeline, routing, auxiliary, distillation, fusion), key enabling technologies, and diverse application scenarios driven by on-device needs like low latency, privacy, personalization, and offline operation. While highlighting the significant potential for creating more efficient, adaptable, and accessible AI, we also discuss persistent challenges including system overhead, inter-model consistency, robust task allocation, evaluation complexity, and security/privacy concerns. Future directions point towards more intelligent adaptive frameworks, deeper model fusion, and expansion into multimodal and embodied AI, positioning LLM-SLM collaboration as a key driver for the next generation of practical and ubiquitous artificial intelligence.