The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Evaluating the Factual Consistency of Abstractive Text Summarization
Open accessAbstract
Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents.We propose a weakly-supervised, model-based approach for verifying factual consistency and identifying conflicts between source documents and a generated summary.Training data is generated by applying a series of rule-based transformations to the sentences of source documents.The factual consistency model is then trained jointly for three tasks: 1) identify whether sentences remain factually consistent after transformation, 2) extract a span in the source documents to support the consistency prediction, 3) extract a span in the summary sentence that is inconsistent if one exists.Transferring this model to summaries generated by several state-of-the art models reveals that this highly scalable approach substantially outperforms previous models, including those trained with strong supervision using standard datasets for natural language inference and fact checking.Additionally, human evaluation shows that the auxiliary span extraction tasks provide useful assistance in the process of verifying factual consistency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In most previous works, factuality has been defined as whether a claim in a text can be supported by evidence from a separate, trustworthy knowledge base, with applications in fact-checking (Thorne et al., 2018b) (where the knowledge base is a large source like Wikipedia) and summarization (Kryscinski et al., 2020) (where the knowledge base is an input document or documents).”
From FacTool: Factuality Detection in Generative AI - A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios (2023) · cites this paper as Kryscinski et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Additionally, hallucinations are observed over a wide range of tasks beyond pure fact verification (Kryscinski et al., 2020; Maynez et al., 2020).”
From SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models (2023) · cites this paper as Kryscinski et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Research suggests that up to 30% of machine-generated abstractive summaries may contain factual inconsistencies [52, 53].”
From All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs? (2026) · cites this paper as [53]
The cited source says what the claim attributes to it.
In the citing paper
“Results show that the performance of their FactCC model surpasses the classifiers trained on the MNLI or FEVER datasets.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [126]
The cited source says what the claim attributes to it.
In the citing paper
“These methods, such as entity swapping and sentence negation (Kryscinski et al., 2020;Goyal and Durrett, 2021), were designed to target specific error types that occurred in claims from earlier summarization models.”
From MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents (2024) · cites this paper as Kryscinski et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“In response to this challenge, a surge of research explores leveraging data-augmentation methods to construct synthetical data for fine-tuning the classifier, either by rule-based perturbation [79, 152, 266] or generation [389].”
From A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2025) · cites this paper as [152]
The cited source says what the claim attributes to it.
In the citing paper
“most prior studies have primarily concentrated on task-specific hallucinations, such as abstractive summarization [81, 102, 152, 208, 236, 310], data-to-text[240, 296], and machine translation [389].”
From A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2025) · cites this paper as [152]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This approach has been widely studied in the summarization literature and recent work in factual precision (Kryscinski et al., 2020; Wang et al., 2020; Gao et al., 2022; Manakul et al., 2023).”
From FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation (2023) · cites this paper as Kryscinski et al., 2020
Experimental — accuracy not yet measured
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
(2017) · Cited by 11,625
(2004) · Cited by 9,718
Get To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342
A Neural Attention Model for Abstractive Sentence Summarization
Rush, A. M., Chopra, S., & Weston, J. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1044 · Cited by 2,932
Research works printed but not linked: 9
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In ICLR.
- Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large an- notated corpus for learning natural language infer- ence. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguis- tics.
- Kyunghyun Cho, Bart van Merrienboer, C ¸aglar Gülc ¸ehre, Dzmitry Bahdanau, Fethi Bougares, Hol- ger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Nat- ural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1724- 1734.
- Alexis Conneau, Ruty Rinott, Guillaume Lample, Ad- ina Williams, Samuel R. Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. Xnli: Evaluating cross- lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Nat- ural Language Processing. Association for Compu- tational Linguistics.
- Sergey Edunov, Myle Ott, Michael Auli, and David Grangier. 2018. Understanding back-translation at scale. CoRR, abs/1808.09381. · arXiv
- Ramesh Nallapati, Bowen Zhou, C ¸aglar Gülc ¸ehre, Bing Xiang, et al. 2016. Abstractive text summa- rization using sequence-to-sequence rnns and be- yond. Proceedings of SIGNLL Conference on Com- putational Natural Language Learning.
- Ramakanth Pasunuru and Mohit Bansal. 2018. Multi- reward reinforced summarization with saliency and entailment. CoRR, abs/1804.06451. · arXiv
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In Proc. of NAACL.
- James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and verification. CoRR, abs/1803.05355. · arXiv
Cited by
Sorted by citations
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688
“…detection benchmarks, most prior studies have primarily concentrated on task-specific hallucinations, such as abstractive summarization (Kryscinski et al., 2020; Wang et al., 2020a; Maynez et al., 2020; Fabbri et al., 2021; Goyal and Durrett, 2021; Pagnoni et al., 2021; Tang et al.,…”
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.153 · Cited by 948
Metadata
- Authors
- Kryscinski, W., McCann, B., Xiong, C., & Socher, R.
- Affiliations
- Salesforce (United States) (US)
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Pages
- 9332-9346
- OpenAlex
- W2981456979
- Cited by
- 669
- References
- 41
- Citations by year
- 2026: 94 · 2025: 86 · 2024: 56 · 2023: 171 · 2022: 106 · 2021: 118 · 2020: 37
- FWCI
- 41.26
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- abstractive summarization, factual consistency, weakly supervised learning, rule-based transformation, span extraction, natural language inference, fact-checking, summarization evaluation metrics
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
