Dany-0
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
Community
[🚀SurveyX——Automated Academic Survey Generation Engine💡]
When the pace of technological iteration surpasses the limits of human cognition⏳
Are you still manually organizing a massive volume of literature in the traditional way?📚
＞＞＞Let SurveyX open a new paradigm of intelligent research for you✨＜＜＜
SurveyX, with LLM as its core engine🧠, creates a fully automated survey paper generation⚙️.
Simply provide a title and keywords, and it will automatically conduct literature retrieval and generate a scholarly review paper comparable to human-level quality📄, achieving a full research cycle from literature tracking to final output🎯!
Key features of SurveyX include:
- ⚡ Efficient search algorithms that ensure broad coverage while accurately selecting highly relevant content
- 🌳 Innovative "attribute tree" preprocessing algorithm, efficiently extracting key information from literature like a human
- 🖼️ Exquisite chart presentations, using multimodal technology and information extraction methods to generate expressive images and tables
🔗arxiv link: https://arxiv.org/abs/2502.14776
🐙github link: https://github.com/IAAR-Shanghai/SurveyX
🚀Our website: www.surveyx.cn
You can generate the paper you want through GitHub.
Try SurveyX now and experience:
√ Enter research keywords and review title in the morning
√ Get a complete review framework by lunchtime
√ Complete a final PDF draft comparable to professional scholars by the end of the workday📑
While I appreciate the efforts here, I cannot find detailed discussions around the ethical implications for systems like these (please correct me if I missed this). I am somewhat against an end-to-end «arxiv like» paper, rather than just producing a regular document in a similar fashion, as it more or less welcomes people to publish unverified information.
Thank you for raising this important concern. We fully understand and share your emphasis on the ethical implications of automated systems like SurveyX. It’s worth noting that we have had measures in place to ensure the responsible use of the generated content:
Watermarking and Disclaimer: Every generated document includes a watermark and a clear disclaimer on the last page stating, "The generated content should not be used for academic publication or formal submissions and must be independently reviewed and verified."
Formatting for Readability: The current formatting is designed to enhance readability and is not intended to mimic formal academic papers. Our goal is to assist researchers in organizing and synthesizing information, not to replace rigorous academic review or verification.
Encouraging Verification: We actively encourage users to treat the generated content as a starting point for further research and analysis, rather than a final product.
We are committed to fostering responsible use of AI in academia and welcome further discussions on how to improve ethical safeguards. If you have additional suggestions, we’d be grateful to hear them!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ASTRAL: Automated Safety Testing of Large Language Models (2025)
- A Survey on Large Language Models with some Insights on their Capabilities and Limitations (2025)
- Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation (2025)
- Large language models for automated scholarly paper review: A survey (2025)
- CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering (2025)
- VRank: Enhancing Verilog Code Generation from Large Language Models via Self-Consistency (2025)
- Foundations of Large Language Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper