# Instruct Large Language Models to Generate Scientific Literature Survey Step by Step

arXiv: https://arxiv.org/abs/2408.07884 · HTML: https://mlsanity.com/paper/2408.07884/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [On Interpretability of Artificial Neural Networks: A Survey](https://mlsanity.com/paper/2001.02522/) (2020)
- [Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models](https://mlsanity.com/paper/2404.13919/) (2024)

## Built on by (most cited first, 10 of 10)

- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)
- [SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models](https://mlsanity.com/paper/2508.17647/) (2025)
- [Completing A Systematic Review in Hours instead of Months with Interactive AI Agents](https://mlsanity.com/paper/2504.14822/) (2025)
- [SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing](https://mlsanity.com/paper/2508.14317/) (2025)
- [TaxoAlign: Scholarly Taxonomy Generation Using Language Models](https://mlsanity.com/paper/2510.17263/) (2025)
- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)
- [MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio](https://mlsanity.com/paper/2606.17041/) (2026)
- [SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation](https://mlsanity.com/paper/2609.05938/) (2026)

## Abstract (arXiv)

Abstract. Automatically generating scientific literature surveys is a valuable task that can significantly enhance research efficiency. However, the diverse and complex nature of information within a literature survey poses substantial challenges for generative models. In this paper, we design a series of prompts to systematically leverage large language models (LLMs), enabling the creation of comprehensive literature surveys through a step-by-step approach. Specifically, we design prompts to guide LLMs to sequentially generate the title, abstract, hierarchical headings, and the main content of the literature survey. We argue that this design enables the generation of the headings from a high-level perspective. During the content generation process, this design effectively harnesses relevant information while minimizing costs by restricting the length of both input and output content in LLM queries. Our implementation with Qwen-long achieved third place in the NLPCC 2024 Scientific Literature Survey Generation evaluation task, with an overall score only 0.03% lower than the second-place team. Additionally, our soft heading recall is 95.84%, the second best among the submissions. Thanks to the efficient prompt design and the low cost of the Qwen-long API, our method reduces the expense for generating each literature survey to 0.1 RMB, enhancing the practical value of our method.