Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models

TL;DR

This survey thoroughly examines hallucinations in large language models, analyzing their causes, detection methods, and solutions to improve reliability and reduce misinformation in critical sectors.

Contribution

It provides a comprehensive categorization and analysis of hallucination causes, detection strategies, and evaluates current solutions to address this challenge in LLMs.

Findings

Identified key causes of hallucinations in LLMs

Evaluated effectiveness of existing detection methods

Proposed directions for developing better solutions

Abstract

Edgar Allan Poe noted, "Truth often lurks in the shadow of error," highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions of cognitive and informational asymmetry. This dynamic is strikingly evident in large language models (LLMs). Despite their impressive linguistic generation capabilities, LLMs sometimes produce information that appears factually accurate but is, in reality, fabricated, an issue often referred to as 'hallucinations'. The prevalence of these hallucinations can mislead users, affecting their judgments and decisions. In sectors such as finance, law, and healthcare, such misinformation risks causing substantial economic losses, legal disputes, and health risks, with wide-ranging consequences.In our research, we have methodically categorized, analyzed the causes, detection methods, and solutions related to LLM hallucinations. Our efforts have particularly focused on understanding the roots of hallucinations and evaluating the efficacy of current strategies in revealing the underlying logic, thereby paving the way for the development of innovative and potent approaches. By examining why certain measures are effective against hallucinations, our study aims to foster a comprehensive approach to tackling this issue within the domain of LLMs.