Cognitive Mirage: A Review of Hallucinations in Large Language Models

TL;DR

This paper reviews hallucinations in large language models, offering a taxonomy, analyzing detection and mitigation methods, and proposing future research directions to address this critical issue in AI text generation.

Contribution

It introduces a comprehensive taxonomy of hallucinations, provides theoretical insights and analysis, and suggests future research avenues for improving LLM reliability.

Findings

Taxonomy of hallucinations in various text tasks

Analysis of detection and mitigation methods

Proposed future research directions

Abstract

As large language models continue to develop in the field of AI, text generation systems are susceptible to a worrisome phenomenon known as hallucination. In this study, we summarize recent compelling insights into hallucinations in LLMs. We present a novel taxonomy of hallucinations from various text generation tasks, thus provide theoretical insights, detection methods and improvement approaches. Based on this, future research directions are proposed. Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future. As hallucinations garner significant attention from the community, we will maintain updates on relevant research progress.