SurveyX: Academic Survey Automation via Large Language Models
This work addresses the need for efficient academic survey automation, offering a domain-specific solution with incremental improvements over prior methods.
The paper tackles the problem of automated survey generation by proposing SurveyX, a system that decomposes the process into preparation and generation phases, resulting in improvements of 0.259 in content quality and 1.76 in citation quality compared to existing systems.
Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated survey generation. However, recent research related to automated survey generation remains constrained by some critical limitations like finite context window, lack of in-depth content discussion, and absence of systematic evaluation frameworks. Inspired by human writing processes, we propose SurveyX, an efficient and organized system for automated survey generation that decomposes the survey composing process into two phases: the Preparation and Generation phases. By innovatively introducing online reference retrieval, a pre-processing method called AttributeTree, and a re-polishing process, SurveyX significantly enhances the efficacy of survey composition. Experimental evaluation results show that SurveyX outperforms existing automated survey generation systems in content quality (0.259 improvement) and citation quality (1.76 enhancement), approaching human expert performance across multiple evaluation dimensions. Examples of surveys generated by SurveyX are available on www.surveyx.cn