Automated Review Generation Method Based on Large Language Models
This addresses efficiency bottlenecks for researchers across fields by automating literature review generation, though it is incremental as it applies existing LLMs to a new task.
The authors tackled the problem of overwhelming literature volumes by developing an automated review generation method using large language models, which matched or exceeded manual quality and analyzed 343 articles in seconds per article, reducing hallucination risks to below 0.5% with 95% confidence.
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.