SurveyX: Academic Survey Automation via Large Language Models

TL;DR

SurveyX leverages large language models and innovative techniques like online reference retrieval and AttributeTree to automate survey creation, significantly improving quality and approaching human expert standards.

Contribution

The paper introduces SurveyX, a novel system for automated survey generation that decomposes the process into two phases and incorporates new methods to enhance content and citation quality.

Findings

Outperforms existing systems in content quality by 0.259

Improves citation quality by 1.76

Approaches human expert performance in multiple evaluation metrics

Abstract

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