Automated Review Generation Method Based On Large Language Models

Wu Shican, Ma Xiao, Luo Dehui, Li Lulu, Shi Xiangcheng, Chang Xin, Lin Xiaoyun, Luo Ran, Pei Chunlei, Zhao Zhi-jian, Gong Jinlong. Arxiv 2024

[Paper]    
Fine Tuning RAG Survey Paper

Literature research, vital for scientific advancement, is overwhelmed by the vast ocean of available information. Addressing this, we propose an automated review generation method based on Large Language Models (LLMs) to streamline literature processing and reduce cognitive load. In case study on propane dehydrogenation (PDH) catalysts, our method swiftly generated comprehensive reviews from 343 articles, averaging seconds per article per LLM account. Extended analysis of 1041 articles provided deep insights into catalysts’ composition, structure, and performance. Recognizing LLMs’ hallucinations, we employed a multi-layered quality control strategy, ensuring our method’s reliability and effective hallucination mitigation. Expert verification confirms the accuracy and citation integrity of generated reviews, demonstrating LLM hallucination risks reduced to below 0.5% with over 95% confidence. Released Windows application enables one-click review generation, aiding researchers in tracking advancements and recommending literature. This approach showcases LLMs’ role in enhancing scientific research productivity and sets the stage for further exploration.

Similar Work