A Concise Review of Hallucinations in LLMs and their Mitigation

📅 2025-12-02
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This paper systematically surveys hallucination in large language models (LLMs), clarifying its root causes—including training data bias, decoding-induced distortion, and incomplete knowledge representation—and classifying its multidimensional manifestations (e.g., factual, logical, and consistency hallucinations). Methodologically, it proposes a unified hallucination taxonomy and establishes a three-layer mitigation framework—detection, attribution, and suppression—that integrates major technical paradigms: pretraining interventions, prompt engineering, retrieval-augmented generation, and post-hoc correction. Through structured literature analysis and mechanistic dissection of representative approaches, the work delivers the first practice-oriented, one-stop knowledge portal for hallucination governance. The resulting concise survey document enhances research reproducibility and accelerates real-world deployment, providing both theoretical foundations and methodological guidance for advancing LLM trustworthiness.

Technology Category

Application Category

📝 Abstract
Traditional language models face a challenge from hallucinations. Their very presence casts a large, dangerous shadow over the promising realm of natural language processing. It becomes crucial to understand the various kinds of hallucinations that occur nowadays, their origins, and ways of reducing them. This document provides a concise and straightforward summary of that. It serves as a one-stop resource for a general understanding of hallucinations and how to mitigate them.
Problem

Research questions and friction points this paper is trying to address.

Summarizes types and origins of LLM hallucinations
Reviews methods to reduce hallucinations in language models
Provides a concise resource on hallucination mitigation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Summarizes hallucination types and origins
Reviews mitigation methods for LLM hallucinations
Provides concise resource for understanding hallucinations
🔎 Similar Papers
No similar papers found.
P
Parth Pulkundwar
Computer Engineering, K J Somaiya Institute of Technology, Mumbai, India
V
Vivek Dhanawade
Artificial Intelligence and Data Science, K J Somaiya Institute of Technology, Mumbai, India
R
Rohit Yadav
Information Technology, K J Somaiya Institute of Technology, Mumbai, India
M
Minal Sonkar
Computer Engineering, K J Somaiya Institute of Technology, Mumbai, India
M
Medha Asurlekar
Artificial Intelligence and Data Science, K J Somaiya Institute of Technology, Mumbai, India
S
Sarita Rathod
Information Technology, K J Somaiya Institute of Technology, Mumbai, India