Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.

Assessing The Factual Accuracy of Generated Text

Open access
Goodrich, Ben, Rao, Vinay, Liu, Peter J., Saleh, Mohammad · 2019 · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Abstract

We propose a model-based metric to estimate the factual accuracy of generated text that is complementary to typical scoring schemes like ROUGE (Recall-Oriented Understudy for Gisting Evaluation) and BLEU (Bilingual Evaluation Understudy). We introduce and release a new large-scale dataset based on Wikipedia and Wikidata to train relation classifiers and end-to-end fact extraction models. The end-to-end models are shown to be able to extract complete sets of facts from datasets with full pages of text. We then analyse multiple models that estimate factual accuracy on a Wikipedia text summarization task, and show their efficacy compared to ROUGE and other model-free variants by conducting a human evaluation study.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3292500.3330955

Cites

51 of 51 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY-NC-SA · From the PDF
Image 2
CC-BY-NC-SA · From the PDF
Figure 2 A screenshot of the interface presented to human evaluators to judge the factual accuracies of generated text. The ground-truth text is shown on the left, with the model generated text on the right. The evaluator is then asked to rate the factual accuracy of the generated text on a five point scale of 'Very Poor' to 'Very Good'
Figure 2 A screenshot of the interface presented to human evaluators to judge the factual accuracies of generated text. The ground-truth text is shown on the left, with the model generated text on the right. The evaluator is then asked to rate the factual accuracy of the generated text on a five point scale of 'Very Poor' to 'Very Good'CC-BY-NC-SA · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 49 references

Research works printed but not linked: 19

  1. Bahdanau Dzmitry, 2015, International Conference on Learning Representations .
  2. Banko Michele, 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc.
  3. Cao Ziqiang, 2017, CoRR
  4. Clark Kevin, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, 643--653
  5. 10.5555/1626355.1626389 · doi:10.5555/1626355.1626389
  6. Liu Peter J., 2018, Proceedings of the 2018 International Conference on Learning Representations .
  7. Mccallum Andrew, 2003, Relational Models. In In Proceedings of the IJCAI-2003 Workshop on Learning Statistical Models from Relational Data .
  8. 10.5555/1690219.1690287 · doi:10.5555/1690219.1690287
  9. Mohamed Thahir P., Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics
  10. Nenkova Ani, 2004, Passonneau
  11. 10.5555/1870658.1870706 · doi:10.5555/1870658.1870706
  12. Recasens Marta, 2013, Proceedings of the 2013 North American Chapter of the Association for Computational Linguistics .
  13. Riedel Sebastian, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 74--84
  14. Serban Iulian Vlad, Proceedings of the 2017 AAAI Conference on Artificial Intelligence. 3288--3294
  15. Serban Iulian Vlad, 2017, Sai Mudumba, Alexandre de Bré bisson, Jose Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau
  16. Surdeanu Mihai, Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics
  17. Vaswani Ashish, 2018, Aidan N. Gomez, Stephan Gouws, Llion Jones, Łukasz Kaiser, Nal Kalchbrenner, Niki Parmar, Ryan Sepassi, Noam Shazeer, and Jakob Uszkoreit.
  18. Wiseman Sam, 2017, Rush
  19. Wu Yonghui, 2016, CoRR

Cited by

See all 184

Metadata

Authors
Goodrich, B., Rao, V., Liu, P. J., & Saleh, M.
Affiliations
Google (United States) (US)
Venue
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Publisher
ACM
Published
2019-07-25
Pages
166-175
OpenAlex
W2947681066
Cited by
162
References
49
Citations by year
2026: 7 · 2025: 21 · 2024: 17 · 2023: 28 · 2022: 34 · 2021: 30 · 2020: 24 · 2019: 1
FWCI
8.51
Type
conference paper
Language
en
Open access
Locations
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by-nc-sa)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
Keywords
factual accuracy, fact extraction, relation extraction, Wikipedia, Wikidata, text summarization, ROUGE, BLEU, large-scale datasets

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Assessing The Factual Accuracy of Generated Text. https://app.cochat.ai/papers/10.1145/3292500.3330955
The paper
Goodrich, B., Rao, V., Liu, P. J., & Saleh, M. (2019). Assessing The Factual Accuracy of Generated Text. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. https://doi.org/10.1145/3292500.3330955

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.