mlsanityData to 7 Oct 2026

A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

arXiv 1606.02858 ↗First posted 9 Jun 2016cs.CL cs.AIcited by 71

Not on the map. Why?

Abstract (arXiv)

Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP. A key factor impeding its solution by machine learned systems is the limited availability of human-annotated data. Hermann et al. (2015) seek to solve this problem by creating over a million training examples by pairing CNN and Daily Mail news articles with their summarized bullet points, and show that a neural network can then be trained to give good performance on this task. In this paper, we conduct a thorough examination of this new reading comprehension task. Our primary aim is to understand what depth of language understanding is required to do well on this task. We approach this from one side by doing a careful hand-analysis of a small subset of the problems and from the other by showing that simple, carefully designed systems can obtain accuracies of 73.6% and 76.6% on these two datasets, exceeding current state-of-the-art results by 7-10% and approaching what we believe is the ceiling for performance on this task.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 18; 2023: 10; 2024: 8; 2025: 9; 2026: 6.

71 papers.

Sort:

By area:

  1. 2024Large Language Models: A Surveycited by 506
  2. 2022WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creationcited by 200
  3. 2024Are We Done with MMLU?cited by 178
  4. 2022Impact of Pretraining Term Frequencies on Few-Shot Reasoningcited by 142
  5. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 108
  6. 2021Competency Problems: On Finding and Removing Artifacts in Language Datacited by 91
  7. 2024Asymmetry in Low-Rank Adapters of Foundation Modelscited by 81
  8. 2022An Empirical Survey on Long Document Summarization: Datasets, Models and Metricscited by 74
  9. 2023Compressing LLMs: The Truth is Rarely Pure and Never Simplecited by 59
  10. 2022Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasetscited by 54
  11. 2021Why Machine Reading Comprehension Models Learn Shortcuts?cited by 40
  12. 2021Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistantscited by 31
38 more
  1. 2023Explanation-based Finetuning Makes Models More Robust to Spurious Cuescited by 24
  2. 2024From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applicationscited by 24
  3. 2024FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skippingcited by 23
  4. 2022Saving Dense Retriever from Shortcut Dependency in Conversational Searchcited by 18
  5. 2021On the Robustness of Reading Comprehension Models to Entity Renamingcited by 17
  6. 2022TVShowGuess: Character Comprehension in Stories as Speaker Guessingcited by 17
  7. 2021Neural ranking models for document retrievalcited by 16
  8. 2021How well do you know your summarization datasets?cited by 16
  9. 2022Machine Reading, Fast and Slow: When Do Models "Understand" Language?cited by 13
  10. 2023GLoRE: Evaluating Logical Reasoning of Large Language Modelscited by 13
  11. 2021Mitigating the Position Bias of Transformer Models in Passage Re-Rankingcited by 10
  12. 2022A Survey of Machine Narrative Reading Comprehension Assessmentscited by 10
  13. 2024Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errorscited by 9
  14. 2023Does Synthetic Data Make Large Language Models More Efficient?cited by 8
  15. 2021CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Levelcited by 5
  16. 2022WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Languagecited by 5
  17. 2022Data Augmentation for Biomedical Factoid Question Answeringcited by 5
  18. 2023On Evaluation of Document Classification using RVL-CDIPcited by 5
  19. 2024TIGQA:An Expert Annotated Question Answering Dataset in Tigrinyacited by 5
  20. 2025ImpRAG: Retrieval-Augmented Generation with Implicit Queriescited by 5
  21. 2021Fact-driven Logical Reasoning for Machine Reading Comprehensioncited by 4
  22. 2025KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoningcited by 4
  23. 2021Human Attention during Goal-directed Reading Comprehension Relies on Task Optimizationcited by 3
  24. 2021Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervisioncited by 3
  25. 2023Automated Testing and Improvement of Named Entity Recognition Systemscited by 3
  26. 2026A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inferencecited by 3
  27. 2021Model Agnostic Answer Reranking System for Adversarial Question Answeringcited by 2
  28. 2021Towards Solving Multimodal Comprehensioncited by 2
  29. 2021A Coarse to Fine Question Answering System based on Reinforcement Learningcited by 2
  30. 2021Interactive Machine Comprehension with Dynamic Knowledge Graphscited by 2
  31. 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
  32. 2021Building a Question and Answer System for News Domaincited by 1
  33. 2021PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policiescited by 1
  34. 2021Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmarkcited by 1
  35. 2022POTATO: exPlainable infOrmation exTrAcTion framewOrkcited by 1
  36. 2022A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metricscited by 1
  37. 2022A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approachescited by 1
  38. 2023Revisiting Automatic Question Summarization Evaluation in the Biomedical Domaincited by 1

50 most cited of 71 All 71 (JSON)