Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

TL;DR

This survey reviews various strategies for enhancing large language models with structured context, including in-context learning, retrieval augmentation, and causal reasoning, emphasizing their comparative effectiveness and deployment considerations.

Contribution

It offers a unified framework, a transparent literature review protocol, and a structured evidence synthesis for augmentation methods in large language models.

Findings

Structured context improves LLM reasoning and knowledge retrieval.

Higher-confidence findings are distinguished from emerging results.

Deployment frameworks guide trustworthy retrieval-augmented NLP.

Abstract

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.