Automated Review Generation Method Based on Large Language Models

TL;DR

This paper introduces an automated review generation method using large language models that efficiently produces high-quality scientific literature reviews, reducing researcher workload and mitigating hallucination risks.

Contribution

The paper presents a novel LLM-based framework for automatic literature review generation with validated quality and a practical Windows application for broad scientific use.

Findings

Generated reviews match or surpass manual quality.

Reviewed 343 articles in seconds per article.

Hallucination risk reduced below 0.5% with expert verification.

Abstract

Literature research, vital for scientific work, faces the challenge of surging information volumes exceeding researchers' processing capabilities. We present an automated review generation method based on large language models (LLMs) to overcome efficiency bottlenecks and reduce cognitive load. Our statistically validated evaluation framework demonstrates that the generated reviews match or exceed manual quality, offering broad applicability across research fields without requiring users' domain knowledge. Applied to propane dehydrogenation (PDH) catalysts, our method swiftly analyzed 343 articles, averaging seconds per article per LLM account, producing comprehensive reviews spanning 35 topics, with extended analysis of 1041 articles providing insights into catalysts' properties. Through multi-layered quality control, we effectively mitigated LLMs' hallucinations, with expert verification confirming accuracy and citation integrity while demonstrating hallucination risks reduced to below 0.5\% with 95\% confidence. Released Windows application enables one-click review generation, enhancing research productivity and literature recommendation efficiency while setting the stage for broader scientific explorations.