Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
Essential reference for ML engineers designing RAG systems and researchers exploring LLM augmentation techniques.
AI Summary
A comprehensive technical survey examining contextual enrichment strategies in LLMs, ranging from in-context prompting to advanced causal retrieval-augmented generation (CausalRAG). The paper analyzes how structured context supplied at time addresses fundamental limitations in knowledge, context windows, and reasoning capabilities.
Excerpt
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 pr