通过语义分解与上下文筛选提升大模型的上下文理解能力。
Semantic Decomposition and Selective Context Filtering -- Text Processing Techniques for Context-Aware NLP-Based Systems
- 将输入提示分解为层次化信息结构，便于系统处理
- 可系统性过滤无关上下文内容，提升响应相关性
- 适合需要动态接口和复杂流程优化的智能系统
本文提出两种适用于上下文感知系统的文本处理技术：语义分解（Semantic Decomposition），将输入提示逐层分解为结构化、层次化的信息模式，使系统更易解析与处理；选择性上下文过滤（Selective Context Filtering），可系统性剔除输入管道中特定无关的上下文信息。探讨了这些技术如何帮助上下文感知系统实现动态的大模型-系统接口，增强大模型生成更符合上下文的用户响应的能力，并优化复杂的自动化工作流与处理管道。
原文摘要 · Abstract (English)
In this paper, we present two techniques for use in context-aware systems: Semantic Decomposition, which sequentially decomposes input prompts into a structured and hierarchal information schema in which systems can parse and process easily, and Selective Context Filtering, which enables systems to systematically filter out specific irrelevant sections of contextual information that is fed through a system's NLP-based pipeline. We will explore how context-aware systems and applications can utilize these two techniques in order to implement dynamic LLM-to-system interfaces, improve an LLM's ability to generate more contextually cohesive user-facing responses, and optimize complex automated workflows and pipelines.
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。