Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
This paper contains images and descriptions that are offensive in nature.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 2×
“The entailed issues have been discussed for language models, for instance, models producing stereotypical and derogatory content [Bender et al. 2021], and for vision model respectively CV datasets highlighting, e.g., gender and racial biases [Denton et al. 2021; Larrazabal et al. 2020; Steed and…”
BackgroundKuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.00982 · Cited by 3,653
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé, H., & Crawford, K. (2018) · arXiv · doi:10.48550/arxiv.1803.09010 · Cited by 2,474
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., III, H. D., & Crawford, K. (2021) · Communications of the ACM · doi:10.1145/3458723 · Cited by 2,469 · cited 12×
“Here we ask the arguably “circular” question of whether a machine can help us reflect on inappropriate content, answering Question 16 in Datasheets [Gebru et al. 2021].”
BackgroundMethodInfluentialLanguage Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2021) · arXiv · doi:10.48550/arxiv.2106.04554 · Cited by 1,420
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357 · cited 3×
“The most recent and successful models, such as GPT-3 [Brown et al. 2020], CLIP [Radford et al. 2021], DALL-E [Ramesh et al. 2021] and other similar models, are trained on data scraped from the web, e.g. using CommonCrawl.”
BackgroundMethodSemi-supervised Sequence Learning
Dai, A. M., & Le, Q. V. (2015) · arXiv · doi:10.48550/arxiv.1511.01432 · Cited by 994 · cited 1×
“While approaches like semi-supervised sequence learning [Dai and Le 2015] and datasets such as ImageNet [Deng et al. 2009]—especially the ImageNet-ILSVRC-2012 dataset with 1.2 million images— established pre-training approaches, the training data size increased rapidly to billions of training…”
MethodInfluentialTransformer Interpretability Beyond Attention Visualization
Chefer, H., Gur, S., & Wolf, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00084 · Cited by 903
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
Larrazabal, A. J., Nieto, N., Peterson, V., Milone, D. H., & Ferrante, E. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1919012117 · Cited by 685 · cited 1×
“…for language models, for instance, models producing stereotypical and derogatory content [Bender et al. 2021], and for vision model respectively CV datasets highlighting, e.g., gender and racial biases [Denton et al. 2021; Larrazabal et al. 2020; Steed and Caliskan 2021; Wang et al. 2020].”
BackgroundStereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.416 · Cited by 643
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2020) · arXiv · doi:10.48550/arxiv.2004.09456 · Cited by 643 · cited 2×
“A vast body of work to date that describes methodologies to tackle, abusive, offensive, hateful [19], toxic [22], stereotypical [32] or otherwise biased content [13] come from NLP.”
BackgroundHow Much Knowledge Can You Pack into the Parameters of a Language Model?
Roberts, A., Raffel, C., & Shazeer, N. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.437 · Cited by 638
Multimodal Few-Shot Learning with Frozen Language Models
Tsimpoukelli, M., Menick, J., Cabi, S., Eslami, S. M. A., Vinyals, O., & Hill, F. (2021) · arXiv · doi:10.48550/arxiv.2106.13884 · Cited by 355
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
Qin, G., & Eisner, J. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.410 · Cited by 342 · cited 4×
“Several variations employ prompt-tuning: Prefix-tuning, for example, learns a prefix to add to a sample’s embedding [Qin and Eisner 2021] on every model layer.”
MethodInfluentialDocumenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
Dodge, J., Sap, M., Marasović, A., Agnew, W., Ilharco, G., Groeneveld, D., Mitchell, M., & Gardner, M. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.98 · Cited by 306 · cited 1×
“[14] documented the very large C4 corpus with features such as ‘text source’ and ‘content’, arguing for different levels of documentation.”
BackgroundLarge pre-trained language models contain human-like biases of what is right and wrong to do
Schramowski, P., Turan, C., Andersen, N., Rothkopf, C. A., & Kersting, K. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00458-8 · Cited by 291
Self-citationLarge image datasets: A pyrrhic win for computer vision?
Birhane, A., & Prabhu, V. U. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00158 · Cited by 257 · cited 12×
“Birhane and Prabhu [3] provided modules to detect faces and post-process them to provide privacy, as well as a pornographic content classifier to remove inappropriate images.”
BackgroundMethodInfluentialYang, K., Qinami, K., Fei-Fei, L., Deng, J., & Russakovsky, O. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3375709 · Cited by 254
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
Dhamala, J., Sun, T., Kumar, V., Krishna, S., Pruksachatkun, Y., Chang, K.-W., & Gupta, R. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445924 · Cited by 244 · cited 1×
“A vast body of work to date that describes methodologies to tackle, abusive, offensive, hateful [Glavaš et al. 2020], toxic [Han and Tsvetkov 2020], stereotypical [Nadeem et al. 2021] or otherwise biased content [Dhamala et al. 2021] come from NLP.”
BackgroundSelf-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP
Schick, T., Udupa, S., & Schütze, H. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00434 · Cited by 227 · cited 2×
“[41] demonstrated that language models can self-debias the text they produce, specifically regarding toxic output.”
BackgroundResultOn the genealogy of machine learning datasets: A critical history of ImageNet
Denton, E., Hanna, A., Amironesei, R., Smart, A., & Nicole, H. (2021) · Big Data & Society · doi:10.1177/20539517211035955 · Cited by 221 · cited 1×
“…for language models, for instance, models producing stereotypical and derogatory content [Bender et al. 2021], and for vision model respectively CV datasets highlighting, e.g., gender and racial biases [Denton et al. 2021; Larrazabal et al. 2020; Steed and Caliskan 2021; Wang et al. 2020].”
BackgroundLarge image datasets: A pyrrhic win for computer vision?
Prabhu, V. U., & Birhane, A. (2020) · arXiv · doi:10.48550/arxiv.2006.16923 · Cited by 91
MAGMA – Multimodal Augmentation of Generative Models through Adapter-based Finetuning
Eichenberg, C., Black, S., Weinbach, S., Parcalabescu, L., & Frank, A. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.179 · Cited by 49
Research works printed but not linked: 24
- Jack Bandy and Nicholas Vincent. 2021. Addressing ”Documentation Debt” in Machine Learning Research: A Retrospective Datasheet for BookCorpus. In Proceedings of NeurIPS Datasets and Benchmarks. 1–13.
- Andy Brock, Soham De, Samuel L. Smith, and Karen Simonyan. 2021. High-Performance Large-Scale Image Recognition Without Normalization. In Proceedings of the 38th International Conference on Machine Learning, (ICML). 1059–1071.
- Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Proceedings of Annual Conference on Neural Information Processing Systems (NeurIPS). 1–25.
- Damien L. Crone, Stefan Bode, Carsten Murawski, and Simon M. Laham. 2018. The Socio-Moral Image Database (SMID): A novel stimulus set for the study of social, moral and affective processes. PLOS ONE 13, 1 (01 2018), 1–34.
- Aida Mostafazadeh Davani, Mark Díaz, and Vinodkumar Prabhakaran. 2022. Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations. Transactions of the Association for Computational Linguistics (TACL) 10 (01 2022), 92–110.
- Karan Desai, Gaurav Kaul, Zubin Aysola, and Justin Johnson. 2021. RedCaps: Web-curated image-text data created by the people, for the people. In Proceedings of NeurIPS Datasets and Benchmarks (NeurIPS). 1–13.
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171–4186.
- 10.1109/WACV45572.2020.9093454 · DOI
- 10.18653/v1/2020.coling-main.559 · DOI
- 10.1109/WACV45572.2020.9093414 · DOI · Paper page
- Karen Hambardzumyan, Hrant Khachatrian, and Jonathan May. 2021. WARP: Word-level Adversarial ReProgramming. arXiv preprint arXiv:2101.00121. (2021). · arXiv
- 10.18653/v1/2020.emnlp-main.622 · DOI · Paper page
- 10.1145/3306618.3314267 · DOI · Paper page
- Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the International Conference on Machine Learning, (ICML). 4904–4916.
- 10.1007/s11263-020-01316-z · DOI · Paper page
- Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning (ICML). 8748–8763.
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. CoRR (2019).
- Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. In Proceedings of the International Conference on Machine Learning (ICML). 8821–8831.
- 10.18653/v1/2020.acl-main.486 · DOI · Paper page
- 10.3389/frai.2020.00036 · DOI · Paper page
- 10.1145/3442188.3445932 · DOI · Paper page
- Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning, (ICML)(Proceedings of Machine Learning Research, Vol. 97). 6105–6114.
- Mingxing Tan and Quoc V. Le. 2021. EfficientNetV2: Smaller Models and Faster Training. In Proceedings of the 38th International Conference on Machine Learning, (ICML)(Proceedings of Machine Learning Research, Vol. 139). 10096–10106.
- 10.1007/978-3-030-58580-8_43 · DOI
Cited by
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Schramowski, P., Brack, M., Deiseroth, B., & Kersting, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02157 · Cited by 219
Self-citationDamacena Duarte, J., Cândido, G. D., De Britto Filho, J. R. A., Souza Neto, J., Da Costa, E. J., Da Costa, J. P. J., & Peotta De Melo, L. (2026) · IEEE Access · doi:10.1109/access.2026.3656849 · Cited by 15
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
Qu, Y., Shen, X., Wu, Y., Backes, M., Zannettou, S., & Zhang, Y. (2025) · Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3719027.3765088 · Cited by 6
“To identify a wider range of un-safe content, Chramowski et al. [63] build Q16 using the prompt learning technique on a dataset containing morally negative/positive images.”
Influential
Metadata
- Authors
- Schramowski, P., Tauchmann, C., & Kersting, K.
- Venue
- 2022 ACM Conference on Fairness Accountability and Transparency
- Publisher
- ACM
- Published
- 2022-06-20
- Pages
- 1350-1361
- OpenAlex
- W4283172096
- Cited by
- 63
- References
- 29
- FWCI
- 12.33
- Type
- conference paper
- Language
- en
- Open access
- green
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
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.