让大模型学会把局部创新推广到其他流程阶段。
Scatter-Based Innovation Propagation in Large Language Models for Multi-Stage Process Adaptation
- 通过四步流程识别、泛化并迁移特定阶段的创新
- 在结构相似阶段间成功推广创新，提升模型泛化能力
- 适合需要跨模块复用创意的复杂流程设计场景
大型语言模型（LLMs）虽能复现和扩展预训练中观察到的模式，但在将新想法从原始语境外推时表现不佳。本文针对多阶段流程中局部创新难以迁移的问题，提出基于散射的创新扩展模型（innovation scatter model），引导模型完成四个步骤：(1) 通过对比用户输入与上下文识别核心创新；(2) 去除对具体阶段或组件的依赖以泛化创新；(3) 判断泛化后的创新是否适用于更广泛范围；(4) 在结构相似的其他阶段系统性应用该创新。该模型利用各阶段间的结构冗余，提升新思想的可复用性。验证结果表明，该模型使LLM能够将创新有效扩展至结构相似的阶段，显著增强其通用性和重用能力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) exhibit strong capabilities in reproducing and extending patterns observed during pretraining but often struggle to generalize novel ideas beyond their original context. This paper addresses the challenge of applying such localized innovations - introduced at a specific stage or component - to other parts of a multi-stage process. We propose a scatter-based innovation expansion model (innovation scatter model) that guides the LLM through a four-step process: (1) identifying the core innovation by comparing the user's input with its surrounding context, (2) generalizing the innovation by removing references to specific stages or components, (3) determining whether the generalized innovation applies to a broader scope beyond the original stage, and (4) systematically applying it to other structurally similar stages using the LLM. This model leverages structural redundancy across stages to improve the applicability of novel ideas. Verification results demonstrate that the innovation scatter model enables LLMs to extend innovations across structurally similar stages, thereby enhancing generalization and reuse.
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。