mlsanityData to 14 Oct 2026

SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation

arXiv 2305.15186 ↗First posted 24 May 2023cs.CL cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Automatic literature review generation is one of the most challenging tasks in natural language processing. Although large language models have tackled literature review generation, the absence of large-scale datasets has been a stumbling block to the progress. We release SciReviewGen, consisting of over 10,000 literature reviews and 690,000 papers cited in the reviews. Based on the dataset, we evaluate recent transformer-based summarization models on the literature review generation task, including Fusion-in-Decoder extended for literature review generation. Human evaluation results show that some machine-generated summaries are comparable to human-written reviews, while revealing the challenges of automatic literature review generation such as hallucinations and a lack of detailed information. Our dataset and code are available at https://github.com/tetsu9923/SciReviewGen.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 25 of its 69 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

25 of 69 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2020Longformer: The Long-Document Transformercited by 3,413
  6. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  9. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  10. 2022Galactica: A Large Language Model for Sciencecited by 744
  11. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 478
  12. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
13 more
  1. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  2. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  3. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 214
  4. 2019Deep Learning on Image Denoising: An overviewcited by 128
  5. 2020Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articlescited by 97
  6. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  7. 2021MS2: Multi-Document Summarization of Medical Studiescited by 80
  8. 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73
  9. 2014Growth rates of modern science: A bibliometric analysis based on the number of publications and cited referencescited by 64
  10. 2021Exploring Neural Models for Query-Focused Summarizationcited by 44
  11. 2014Effective Use of Word Order for Text Categorization with Convolutional Neural Networkscited by 40
  12. 2016Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddingscited by 11
  13. 2019A Survey on Deep Learning Architectures for Image-based Depth Reconstructioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 9; 2026: 5.

17 papers.

Sort:

By area:

  1. 2025ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubricscited by 49
  2. 2024SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literaturecited by 41
  3. 2025SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Taskscited by 20
  4. 2025LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generationcited by 10
  5. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  6. 2024Systematic Task Exploration with LLMs: A Study in Citation Text Generationcited by 8
  7. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  8. 2024Automated Review Generation Method Based on Large Language Modelscited by 7
  9. 2025SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Modelscited by 7
  10. 2025SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writingcited by 5
  11. 2025In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysiscited by 2
  12. 2026Agentic AI-Empowered Dynamic Survey Frameworkcited by 2
5 more
  1. 2026SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generationcited by 1
  2. 2025An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literaturecited by 0
  3. 2026How Much Structure Do LLMs Need? Evaluating LLMs for Bibliometric Cluster Descriptioncited by 0
  4. 2026LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platformcited by 0
  5. 2026SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentationcited by 0