CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
We study generating abstractive summaries that are faithful and factually consistent with the given articles.A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and automatically generated erroneous summaries, as negative training data, to train summarization systems that are better at distinguishing between them.We further design four types of strategies for creating negative samples, to resemble errors made commonly by two state-of-the-art models, BART and PEGASUS, found in our new human annotations of summary errors.Experiments on XSum and CNN/Daily Mail show that our contrastive learning framework is robust across datasets and models.It consistently produces more factual summaries than strong comparisons with post error correction, entailmentbased reranking, and unlikelihood training, according to QA-based factuality evaluation.Human judges echo the observation and find that our model summaries correct more errors.REFERENCE: A "rare" short-eared owl found emaciated in Flintshire is now recuperating well, the RSPCA have said.SWAPENT: Flintshire → Bettisfield ⇒ A "rare" short-eared owl found emaciated in Bettisfield is now recuperating well, the RSPCA have said.MASKENT: A "rare" short-eared owl found emaciated in [MASK] is now recuperating well, the RSPCA have said.⇒ A "rare" short-eared owl found emaciated in a field in South Yorkshire is now recuperating well, the RSPCA have said.MASKREL: A "rare" short-eared owl found [MASK] in [MASK] is now recuperating well, the RSPCA have said.⇒ A "rare" short-eared owl found dead in London is now recuperating well, the RSPCA have said.REGENENT: A "rare" short-eared owl found emaciated in ⇒ A "rare" short-eared owl found emaciated in Nottinghamshire is now at a wildlife centre to recover.REGENREL: A "rare" short-eared owl found ⇒ A "rare" short-eared owl found in the grounds of a former coal mine is being cared for by the RSPCA in Somerset.SYSLOWCON: An injured golden owl found in a former coal mine in Lancashire is being cared for by the RSPCA.
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.
Integrity signals
Registry
Cites
Statistics
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.
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
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
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 · cited 4×
“Importantly, these strategies are inspired by our new annotation study on errors made by state-of-the-art summarizers—models fine-tuned from BART (Lewis et al., 2020) and PEGA-SUS (Zhang et al., 2020a)—on two benchmarks: XSum (Narayan et al., 2018) and CNN/DailyMail (CNN/DM) (Hermann et al., 2015).”
BackgroundMethodInfluentialTransformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · cited 1×
“Notably, negative sampling plays a key role in word representation learning (Mikolov et al., 2013) and training large masked language models, such as BERT and ALBERT, to induce better contextual representations (Devlin et al., 2019; Lan et al., 2020).”
BackgroundSupervised Contrastive Learning
Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020) · arXiv · doi:10.48550/arxiv.2004.11362 · Cited by 3,569 · cited 2×
“1 Contrastive learning (CL) has obtained impressive results on many visual processing tasks, such as image classification (Khosla et al., 2020; Chen et al., 2020) and synthesis (Park et al., 2020; Zhang et al., 2021b).”
BackgroundSimCSE: Simple Contrastive Learning of Sentence Embeddings
Gao, T., Yao, X., & Chen, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.552 · Cited by 2,851
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Narayan, S., Cohen, S. B., & Lapata, M. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1206 · Cited by 1,207
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 · cited 3×
“Importantly, these strategies are inspired by our new annotation study on errors made by state-of-the-art summarizers—models fine-tuned from BART (Lewis et al., 2020) and PEGA-SUS (Zhang et al., 2020a)—on two benchmarks: XSum (Narayan et al., 2018) and CNN/DailyMail (CNN/DM) (Hermann et al., 2015).”
BackgroundMethod
Cited by
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
Contrastive Learning Reduces Hallucination in Conversations
Sun, W., Shi, Z., Gao, S., Ren, P., De Rijke, M., & Ren, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26596 · Cited by 69
CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper Summarization
Luo, Z., Xie, Q., & Ananiadou, S. (2023) · arXiv · doi:10.48550/arxiv.2301.11223 · Cited by 18
Wei, P., Yang, X., Liu, S., Wang, L., & Zheng, B. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track · doi:10.18653/v1/2022.naacl-industry.2 · Cited by 9
Self-citationTrusting Your Evidence: Hallucinate Less with Context-aware Decoding
Shi, W., Han, X., Lewis, M., Tsvetkov, Y., Zettlemoyer, L., & Yih, S. W.-T. (2023) · arXiv · doi:10.48550/arxiv.2305.14739 · Cited by 6
“, 2021), optimizing summarization models towards a factual consistency metrics (Nan et al., 2021; Cao and Wang, 2021),”
Background
Metadata
- Authors
- Cao, S., & Wang, L.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 6633-6649
- OpenAlex
- W3199926081
- Cited by
- 132
- References
- 32
- FWCI
- 13.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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: CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.532
- The paper
- Cao, S., & Wang, L. (2021). CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.532
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.