The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Factual Error Correction for Abstractive Summarization Models
Open accessAbstract
Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods.However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge.We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries.The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries.These transformations are inspired by an error analysis of state-of-the-art summarization model outputs.Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset.We also find that transferring from artificial error correction to downstream settings is still very challenging 1 .Article: Jerusalem (CNN)The flame of remembrance burns in Jerusalem, and a song of memory haunts Valerie Braham as it never has before.(...) "Now I truly understand everyone who has lost a loved one," Braham said.Her husband, Philippe Braham, was one of 17 people killed in January's terror attacks in Paris.He was in a kosher supermarket when a gunman stormed in, killing four people, all of them Jewish.(...) Original: Valerie braham was one of 17 people killed in january's terror attacks in paris.(inconsistent) Corrected: Philippe braham was one of 17 people killed in january's terror attacks in paris.(consistent) Article: (...) Thursday's attack by al-Shabaab militants killed 147 people, including 142 students, three security officers and two university security personnel.The attack left 104 people injured, including 19 who are in critical condition, Nkaissery said.(...) Original: 147 people, including 142 students, are in critical condition.(inconsistent) Corrected: 19 people, including 142 students, are in critical condition.(inconsistent) Article: (CNN) Officer Michael Slager's five-year career with the North Charleston Police Department in South Carolina ended after he resorted to deadly force following a routine traffic stop.(...) His back is to Slager, who, from a few yards away, raises his gun and fires.Slager is now charged with murder.The FBI is involved in the investigation of the slaying of the father of four.(...) Original: Slager is now charged with murder.(consistent) Corrected: Michael Slager is now charged with murder.(consistent) Article: (CNN)The announcement this year of a new, original Dr. Seuss book sent a wave of nostalgic giddiness across Twitter, and months before publication, the number of pre-orders for "What Pet Should I Get?" continues to climb.(...) It features the spirited siblings from the beloved classic "One Fish Two Fish Red Fish Blue Fish" and is believed to have been written between 1958 and 1962.(...) Original: Seuss book sent a wave of nostalgic giddiness across twitter.(consistent) Corrected: "One Fish Two Fish Red Fish Blue Fish" book sent a wave of nostalgic giddiness across twitter.(inconsistent)
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?
In the citing paper
“LLMs struggle to generate accurate and up-to-date responses on current topics, due to outdated knowledge, lack of domain-specific expertise, or hallucination13–17.”
From Leveraging long context in retrieval augmented language models for medical question answering (2025) · cites this paper as [13]
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
Jakubův, J., Chvalovský, K., Goertzel, Z., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,648
(2004) · Cited by 9,718
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
Text Summarization with Pretrained Encoders
Liu, Y., & Lapata, M. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1387 · Cited by 1,934
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1912.08777 · Cited by 1,206
Evaluating the Factual Consistency of Abstractive Text Summarization
Kryscinski, W., McCann, B., Xiong, C., & Socher, R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.750 · Cited by 669
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
Fabbri, A., Li, I., She, T., Li, S., & Radev, D. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1102 · Cited by 449
Faithful to the Original: Fact Aware Neural Abstractive Summarization
Cao, Z., Wei, F., Li, W., & Li, S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11912 · Cited by 369
Cited by
Sorted by citations
Items 101–134 of 134
Wang, Y., Zhang, Y., Xu, K., Xu, Y., Wang, Y., & Feng, Q. (2025) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189813 · Cited by 1
Jin, L., Zhao, C., Han, D., Zuo, Z., Liang, Y., Liao, Y., & Tohti, T. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-025-02676-z · Cited by 2
Unsupervised Approach to Multilingual User Comments Summarization.
Žagar, A., & Robnik‐Šikonja, M. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · Cited by 1
Yadav, S., Cobeli, S., & Caragea, C. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583449 · Cited by 1
Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization
Zhu, R., Qi, J., & Lau, J. H. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.377 · Cited by 7
Mitigating Societal Harms in Large Language Models
Kumar, S., Balachandran, V., Njoo, L., Anastasopoulos, A., & Tsvetkov, Y. (2023) · doi:10.18653/v1/2023.emnlp-tutorial.5 · Cited by 1
Improving Consistency for Text Summarization with Energy Functions
Zeng, Q., Yin, Q., Li, Z., Gao, Y., Nag, S., Wang, Z., Yin, B., Ji, H., & Zhang, C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.798 · Cited by 1
Optimization of an Abstract Text Summarization Model based on Entity Awareness and Perturbation
Yao, B., & Ding, G. (2023) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs59936.2023.10435599 · Cited by 1
SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References
Gabburo, M., Garg, S., Koncel-Kedziorski, R., & Moschitti, A. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-short.3 · Cited by 1
Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of SummariesPreprint
Tang, X., Fabbri, A. R., Li, H., Mao, Z., Adams, G., Wang, B., Celikyilmaz, A., Mehdad, Y., & Radev, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.09195 · Cited by 1
Estimation of Summary-to-Text Inconsistency by Mismatched EmbeddingsPreprint
Vasilyev, O., & Bohannon, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.05156
Keep it Simple: Unsupervised Simplification of Multi-Paragraph TextPreprint
Laban, P., Schnabel, T., Bennett, P. N., & Hearst, M. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03444 · Cited by 5
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationPreprint
Cao, S., & Wang, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.09209 · Cited by 15
Natural language processing on noisy text
Dong, R. (2021) · doi:10.17760/d20416553
Toward Fact-aware Abstractive Summarization Method Using Joint LearningPreprint
Mao, X., Chen, L., Ju, S., Wan, X., & Liu, Y. (2022) · Research Square · doi:10.21203/rs.3.rs-2206382/v1
Gu, D., On, B.-W., & Jeong, D. (2022) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2022.20.12.25
Factual Error Correction in Summarization with Retriever-Reader Pipeline
Li, W., Liu, J., & Gao, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30105-6_33
Natural language processing for digital advertising
Jin, Y., & Wanvarie, D. (2021) · Chula Digiverse · doi:10.58837/chula.the.2021.121
Nong, Q., Zhang, X., Jin, Z. G., Gao, C., Shang, W., Du, K., Ding, Z., & Ma, Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4600240
The student becomes the master: Outperforming GPT3 on Scientific Factual Error Correction
Ashok, D., Kulkarni, A., Pham, H., & Póczos, B. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.451
Fact-checking benchmark for the Russian Large Language Models
SberDevices, Kozlova, A., Shevelev, D., & Fenogenova, A. (2023) · Computational Linguistics and Intellectual Technologies · doi:10.28995/2075-7182-2023-22-267-277
Anchor Your Embeddings Through the Storm: Mitigating Instance-to-Document Semantic Gap
Barros, R. M., Arguello, K. K., & Wehrmann, J. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650518 · Cited by 1
Learning Latent Variable for Logical Reasoning in Table-Based Fact Verification
Wu, J., & Hou, M. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651044
Self-citationLarge Language Models for HeXie Management Theory: A Comparative Evaluation of RAG and Finetuning
Xu, Y., Chen, S., Tang, L., Yun, J., Li, G., & Wang, C. (2025) · International Conference on Control Engineering and Artificial Intelligence (CCEAI) · doi:10.1145/3722150.3722167
Methods to Evaluate and Improve the Quality of Text Summarization
Nguyen, H. (2025) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2443390
Ownership Verification of Your NLG Models With Semantic Combination Watermarks
Xie, C., Xiang, T., Guo, S., Chen, B., Wang, N., Li, J., & Zhang, T. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3627978
Hallucinations in Abstractive Text Summarization with Large Language Models
Delpisheh, N., & Chali, Y. (2025) · International Generative AI and Computational Language Modelling Conference (GACLM) · doi:10.1109/gaclm67198.2025.11231924 · Cited by 1
Matsui, G., Ishikawa, H., Akiba, T., Nakajima, Y., & Honma, H. (2025) · International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA) · doi:10.1109/icaicta67604.2025.11335110
Vatsa, D., Pantola, D., Mishra, D., & Dabas, R. (2025) · International Conference on Modeling, Simulation & Intelligent Computing (MoSICom) · doi:10.1109/mosicom67153.2025.11398302
Integrating Unsupervised Learning for the Factual Consistency of Generative Models
Nair, S., & -, Y. S. R. (2026) · Future Internet · doi:10.3390/fi18050235
Temporal and linguistic enrichment for abstractive text summarization using transformer models
Abdalgader, K., Ahmed, F. Y. H., Wassie, B., Kerala, K., Heramo, N., & Gudeta, R. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01710-5
Wang, Y., Jia, R., Zhang, W., Lü, W., Jiang, Y., Zhu, J., Wu, S., & Chen, T. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581682
Summarizing India’s News: IndoSumm and CoheraText for Multi-Document Abstractive Summarization
Motghare, M., Agarwal, M., & Agrawal, A. (2026) · IETE Technical Review · doi:10.1080/02564602.2026.2703143
Metadata
- Authors
- Cao, M., Dong, Y., Wu, J., & Cheung, J. C. K.
- Affiliations
- Mila - Quebec Artificial Intelligence Institute (CA)
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Pages
- 6251-6258
- OpenAlex
- W3102645206
- Cited by
- 132
- References
- 19
- Citations by year
- 2026: 5 · 2025: 16 · 2024: 11 · 2023: 43 · 2022: 29 · 2021: 25 · 2020: 3
- FWCI
- 9.55
- 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)
- Funders
- Compute Canada
- Natural Sciences and Engineering Research Council of Canada
- Fonds de recherche du Québec – Nature et technologies
- 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
- abstractive summarization, factual error correction, factual consistency, post-editing, CNN/DailyMail, self-supervised pre-training, error analysis
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
