小模型与大模型协作，提升性能、降低成本、保障隐私与可信性。
A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness
- 构建四维协作目标框架：性能、成本、隐私、可信度。
- 系统梳理小大模型协同方法与设计范式。
- 适合关注高效智能系统部署的研究者与工程师。
大型语言模型（LLMs）在多个领域取得显著进展，但面临微调成本高、推理延迟大、边缘部署受限及可靠性不足等挑战。小型语言模型（SLMs）具有结构紧凑、高效灵活的特点，具备解决上述问题的潜力。近期研究探索了小大模型协同框架，结合SLMs的专精与高效性、LLMs的泛化与推理能力，以应对不同任务和部署场景下的多样化需求。本文从协同目标出发，系统综述了小大模型协作研究，提出涵盖性能提升、成本效益、云边隐私保护与可信性的四维分类体系。在此框架下，总结代表性方法与设计范式，指出当前开放挑战与未来方向，推动高效且安全的小大模型协同发展。相关论文合集可访问 https://github.com/FairyFali/SLMs-Survey。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved remarkable progress across domains and applications but face challenges such as high fine-tuning costs, inference latency, limited edge deployability, and reliability concerns. Small language models (SLMs), with compact, efficient, and adaptable features, offer promising solutions. Building on this potential, recent research explores collaborative frameworks that integrate their complementary strengths, leveraging SLMs' specialization and efficiency with LLMs' generalization and reasoning to address diverse objectives across tasks and deployment scenarios. Motivated by these developments, this paper presents a systematic survey of SLM-LLM collaboration from the perspective of collaboration objectives. We propose a taxonomy covering four goals: performance enhancement, cost-effectiveness, cloud-edge privacy, and trustworthiness. Under this framework, we review representative methods, summarize design paradigms, and outline open challenges and future directions toward efficient and secure SLM-LLM collaboration. The collected papers are available at https://github.com/FairyFali/SLMs-Survey.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。