Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account of augmentation strategies along a single axis: the degree of structured context supplied at inference time. We cover in-context learning and prompt engineering, Retrieval-Augmented Generation (RAG), GraphRAG, and CausalRAG. Beyond conceptual comparison, we provide a transparent literature-screening protocol, a claim-audit framework, and a structured cross-paper evidence synthesis that distinguishes higher-confidence findings from emerging results. The paper concludes with a deployment-oriented decision framework and concrete research priorities for trustworthy retrieval-augmented NLP.

翻译：大型语言模型（LLM）在其参数中编码了海量的世界知识，然而，它们仍从根本上受限于静态知识、有限的上下文窗口以及结构薄弱的因果推理。本综述沿着单一轴线提供了对增强策略的统一阐述：即推理时提供的结构化上下文程度。我们涵盖了上下文学习与提示工程、检索增强生成（RAG）、图检索增强生成（GraphRAG）和因果检索增强生成（CausalRAG）。除了概念性比较，我们还提供了透明的文献筛选协议、声明审计框架，以及一种结构化的跨论文证据综合方法，用以区分高置信度发现与新兴结果。本文最后提出了一个面向部署的决策框架，以及实现可信赖检索增强自然语言处理的具体研究重点。