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

arXiv cs.CL / 4/6/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper surveys how large language models can be augmented with more structured information at inference time, framing methods along a single axis of “degree of structured context.”
It covers and connects in-context prompting/prompt engineering with retrieval-based approaches including RAG, GraphRAG, and CausalRAG, focusing on overcoming limitations from static parameters and finite context windows.
The survey proposes an explicit literature-screening protocol and a claim-audit framework to separate higher-confidence results from emerging findings across the reviewed work.
It concludes with a deployment-oriented decision framework and concrete research priorities aimed at improving trustworthiness in retrieval-augmented NLP systems.

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.