Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems

TL;DR

This paper surveys strategies like RAG and reasoning to mitigate hallucinations in large language models, emphasizing their integration in real-world applications and analyzing their mechanisms and effectiveness.

Contribution

It provides a systematic taxonomy and unified framework for understanding how RAG and reasoning mitigate hallucinations in LLMs, highlighting their synergistic potential.

Findings

RAG and reasoning effectively reduce knowledge and logic-based hallucinations

Integration of RAG and reasoning enhances LLM reliability in applications

Benchmark evaluations demonstrate improved hallucination mitigation

Abstract

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.