Authors: Bankar Akshada Santosh, Prof. S. K. Said, Prof. M. C. Kolse
Abstract: Large Language Models (LLMs) can produce fluent but factually incorrect statements, known as hallucinations, which limits their reliability in healthcare, law, education and other critical domains. This paper reviews methods that reduce hallucination by grounding generation in external knowledge. Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and conditions the model on them, while Knowledge Graphs (KGs) provide structured, verifiable facts and explicit relations that support multi-hop reasoning. The review explains dense passage retrieval, retrieval-augmented pre-training, graph-based RAG that summarizes communities of related entities, and reasoning that walks over knowledge-graph paths. It also covers evaluation, including truthfulness benchmarks and metrics for faithfulness, context relevance and answer relevance. A hybrid architecture is proposed that combines vector retrieval with knowledge-graph lookup, assembles grounded context, generates answers with citations and verifies claims before responding. Research gaps, objectives, a comparison of grounding strategies and challenges such as retrieval errors, outdated knowledge, graph construction cost and latency are discussed. The review concludes that combining unstructured retrieval with structured knowledge offers a practical route to more accurate and transparent LLM applications.
DOI: https://doi.org/10.5281/zenodo.24037457
