单个大模型难担重任，多模型协作才能应对复杂现实
When One LLM Drools, Multi-LLM Collaboration Rules
- 用多模型协作弥补单模型能力局限
- 通过不同层级信息交互提升输出可靠性
- 适合追求公平、多样与高可靠性的应用
本文主张，在复杂、情境化且主观性强的现实场景中，仅依赖单一通用大模型难以生成可靠结果。我们挑战了当前仅靠单个大模型的现状，倡导多大模型协作以更好体现数据、技能与人群的广泛多样性。首先指出单个大模型无法充分代表真实世界的数据分布、异质技能和多元群体，且仅通过进一步训练无法轻易弥合这些表征差距。接着，我们基于访问与信息交换层次，将现有多大模型协作方法划分为四个层级：API级、文本级、对数级和权重级。在此基础上，阐明多模型协作如何解决单模型在可靠性、民主化与多元性方面的难题。最后，指出现有方法的局限，并呼吁未来研究。我们视多模型协作为实现组合智能与协同人工智能发展的关键路径。
原文摘要 · Abstract (English)
This position paper argues that in many realistic (i.e., complex, contextualized, subjective) scenarios, one LLM is not enough to produce a reliable output. We challenge the status quo of relying solely on a single general-purpose LLM and argue for multi-LLM collaboration to better represent the extensive diversity of data, skills, and people. We first posit that a single LLM underrepresents real-world data distributions, heterogeneous skills, and pluralistic populations, and that such representation gaps cannot be trivially patched by further training a single LLM. We then organize existing multi-LLM collaboration methods into a hierarchy, based on the level of access and information exchange, ranging from API-level, text-level, logit-level, to weight-level collaboration. Based on these methods, we highlight how multi-LLM collaboration addresses challenges that a single LLM struggles with, such as reliability, democratization, and pluralism. Finally, we identify the limitations of existing multi-LLM methods and motivate future work. We envision multi-LLM collaboration as an essential path toward compositional intelligence and collaborative AI development.
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。