Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
It addresses hallucination mitigation for reliable LLM deployment in real-world applications, but is incremental as it synthesizes existing approaches.
This survey tackles the problem of hallucination in large language models by analyzing how Retrieval-Augmented Generation (RAG), reasoning enhancement, and their integration in Agentic Systems mitigate it, proposing a taxonomy and unified framework supported by real-world applications and benchmarks.
Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs), particularly in real-world applications. Among various mitigation strategies, Retrieval-Augmented Generation (RAG) and reasoning enhancement have emerged as two of the most effective and widely adopted approaches, marking a shift from merely suppressing hallucinations to balancing creativity and reliability. However, their synergistic potential and underlying mechanisms for hallucination mitigation have not yet been systematically examined. This survey adopts an application-oriented perspective of capability enhancement to analyze how RAG, reasoning enhancement, and their integration in Agentic Systems mitigate hallucinations. We propose a taxonomy distinguishing knowledge-based and logic-based hallucinations, systematically examine how RAG and reasoning address each, and present a unified framework supported by real-world applications, evaluations, and benchmarks.