mlsanityData to 7 Oct 2026

AxCell: Automatic Extraction of Results from Machine Learning Papers

arXiv 2004.14356 ↗First posted 29 Apr 2020cs.CL stat.MLcited by 48

Not on the map. Why?

Abstract (arXiv)

Tracking progress in machine learning has become increasingly difficult with the recent explosion in the number of papers. In this paper, we present AxCell, an automatic machine learning pipeline for extracting results from papers. AxCell uses several novel components, including a table segmentation subtask, to learn relevant structural knowledge that aids extraction. When compared with existing methods, our approach significantly improves the state of the art for results extraction. We also release a structured, annotated dataset for training models for results extraction, and a dataset for evaluating the performance of models on this task. Lastly, we show the viability of our approach enables it to be used for semi-automated results extraction in production, suggesting our improvements make this task practically viable for the first time. Code is available on GitHub.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 11; 2023: 6; 2024: 12; 2025: 8; 2026: 5.

48 papers.

Sort:

By area:

  1. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 174
  2. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  3. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
  4. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
  5. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  6. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  7. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  8. 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Reviewcited by 37
  9. 2024SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literaturecited by 37
  10. 2026AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agentscited by 32
  11. 2023Schema-Driven Information Extraction from Heterogeneous Tablescited by 24
  12. 2021Automated scholarly paper review: Concepts, technologies, and challengescited by 21
36 more
  1. 2022Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurementscited by 21
  2. 2021CitationIE: Leveraging the Citation Graph for Scientific Information Extractioncited by 19
  3. 2021Automated Mining of Leaderboards for Empirical AI Researchcited by 16
  4. 2022STable: Table Generation Framework for Encoder-Decoder Modelscited by 15
  5. 2025How Far Are AI Scientists from Changing the World?cited by 15
  6. 2021Learning to Reason for Text Generation from Scientific Tablescited by 13
  7. 2022Specialized Document Embeddings for Aspect-based Similarity of Research Paperscited by 12
  8. 2023GSAP-NER: A Novel Task, Corpus, and Baseline for Scholarly Entity Extraction Focused on Machine Learning Models and Datasetscited by 12
  9. 2022Business Document Information Extraction: Towards Practical Benchmarkscited by 11
  10. 2024Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboardscited by 10
  11. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  12. 2022A Dataset for N-ary Relation Extraction of Drug Combinationscited by 9
  13. 2022Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documentscited by 6
  14. 2024Effective Context Selection in LLM-based Leaderboard Generation: An Empirical Studycited by 6
  15. 2024On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboardscited by 6
  16. 2022Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answeringcited by 4
  17. 2023CTE: A Dataset for Contextualized Table Extractioncited by 3
  18. 2023S2abEL: A Dataset for Entity Linking from Scientific Tablescited by 3
  19. 2024iTBLS: A Dataset of Interactive Conversations Over Tabular Informationcited by 3
  20. 2024Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIscited by 3
  21. 2025Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMscited by 3
  22. 2025A Position Paper on the Automatic Generation of Machine Learning Leaderboardscited by 3
  23. 2024LEGOBench: Scientific Leaderboard Generation Benchmarkcited by 2
  24. 2024Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5cited by 2
  25. 2025League: Leaderboard Generation on Demandcited by 1
  26. 2025Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mappingcited by 1
  27. 2025Anticipatory Evaluation of Language Modelscited by 1
  28. 2026ModelLens: Finding the Best for Your Task from Myriads of Modelscited by 1
  29. 2026Building Agent Harnesses for Scientific Curation from Multimodal Sourcescited by 1
  30. 2022Data augmentation on graphs for table type classificationcited by 0
  31. 2023Enhancing AI Research Paper Analysis: Methodology Component Extraction using Factored Transformer-based Sequence Modeling Approachcited by 0
  32. 2024Scaling Automatic Extraction of Pseudocodecited by 0
  33. 2024Instruction Finetuning for Leaderboard Generation from Empirical AI Researchcited by 0
  34. 2024RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLUcited by 0
  35. 2026Standardization of Post-Publication Code Verification by Journals is Possible with the Support of the Communitycited by 0
  36. 2026MetaLead: A Comprehensive Human-Curated Leaderboard Dataset for Transparent Reporting of Machine Learning Experimentscited by 0