# SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models

arXiv: https://arxiv.org/abs/2508.17647 · HTML: https://mlsanity.com/paper/2508.17647/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [TLDR: Extreme Summarization of Scientific Documents](https://mlsanity.com/paper/2004.15011/) (2020)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://mlsanity.com/paper/2010.14235/) (2020)
- [MS2: Multi-Document Summarization of Medical Studies](https://mlsanity.com/paper/2104.06486/) (2021)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall](https://mlsanity.com/paper/2410.23000/) (2024)
- [ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor](https://mlsanity.com/paper/2406.14765/) (2024)
- [SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation](https://mlsanity.com/paper/2305.15186/) (2023)
- [Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition](https://mlsanity.com/paper/2412.13612/) (2024)
- [Generating a Structured Summary of Numerous Academic Papers: Dataset and Method](https://mlsanity.com/paper/2302.04580/) (2023)
- [Instruct Large Language Models to Generate Scientific Literature Survey Step by Step](https://mlsanity.com/paper/2408.07884/) (2024)
- [Patterns of authors contribution in scientific manuscripts](https://mlsanity.com/paper/1609.05545/) (2016)

## Built on by (most cited first, 7 of 7)

- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)
- [NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment](https://mlsanity.com/paper/2604.11543/) (2026)
- [pAI/MSc: ML Theory Research with Humans on the Loop](https://mlsanity.com/paper/2604.20622/) (2026)
- [MVSS: A Unified Framework for Multi-View Structured Survey Generation](https://mlsanity.com/paper/2601.09504/) (2026)
- [Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation](https://mlsanity.com/paper/2608.18034/) (2026)
- [SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation](https://mlsanity.com/paper/2609.05938/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## Abstract (arXiv)

Automatic survey generation has emerged as a key task in scientific document processing. While large language models (LLMs) have shown promise in generating survey texts, the lack of standardized evaluation datasets critically hampers rigorous assessment of their performance against human-written surveys. In this work, we present SurveyGen, a large-scale dataset comprising over 4,200 human-written surveys across diverse scientific domains, along with 242,143 cited references and extensive quality-related metadata for both the surveys and the cited papers. Leveraging this resource, we build QUAL-SG, a novel quality-aware framework for survey generation that enhances the standard Retrieval-Augmented Generation (RAG) pipeline by incorporating quality-aware indicators into literature retrieval to assess and select higher-quality source papers. Using this dataset and framework, we systematically evaluate state-of-the-art LLMs under varying levels of human involvement - from fully automatic generation to human-guided writing. Experimental results and human evaluations show that while semi-automatic pipelines can achieve partially competitive outcomes, fully automatic survey generation still suffers from low citation quality and limited critical analysis.