Towards Hybrid Human-AI Workflows for Unknown Unknown Detection
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Predictive models are susceptible to errors called unknown unknowns, in which the model assigns incorrect labels to instances with high confidence. These commonly arise when training data does not represent variations of a class encountered at model deployment. Prior work showed that crowd workers can identify instances of unknown unknowns, but asking the crowd to identify a sufficient number of individual instances can be costly to acquire [2]. Instead, this paper presents an approach that leverages people’s ability to find patterns to retrain classifiers more effectively with fewer examples. We ask crowd workers to suggest and verify patterns in unknown unknowns. We then use these patterns to train an expansion classifier to identify additional examples from existing data that the primary classifier has encountered (and potentially misclassified) in the past. Our experiments show that our approach outperforms existing unknown unknown detection methods at improving classifier performance. This work is the first to leverage crowds to identify error patterns in large datasets to improve ML training.
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
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
Cheap and fast---but is it good?: evaluating non-expert annotations for natural language tasks
Snow, R., O'Connor, B., Jurafsky, D., & Ng, A. Y. (2008) · Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP '08 · doi:10.3115/1613715.1613751 · Cited by 1,887
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Inferring Networks of Substitutable and Complementary Products
McAuley, J., Pandey, R., & Leskovec, J. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783381 · Cited by 645 · cited 1×
“50K random samples of Amazon reviews in the 4 most popular categories: books, CDs and vinyl, movies and TV, and electronics fromMcAuley, Pandey, and Leskovec 2015 [17].”
BackgroundBeat the Machine: Challenging Humans to Find a Predictive Model's “Unknown Unknowns”
Attenberg, J., Ipeirotis, P., & Provost, F. (2015) · Journal of Data and Information Quality · doi:10.1145/2700832 · Cited by 103 · cited 6×
“Prior work in finding unknown unknowns either requires a large budget to query people for example unknown unknowns [2] or relies on clustering algorithms to efficiently query the problem space, whichwe show is ineffective for small blind spots.”
BackgroundMethodInfluential
Research works printed but not linked: 14
- 10.1145/2034691.2034742 · DOI · Paper page
- Gagan Bansal and Daniel S Weld . 2018 . A coverage-based utility model for identifying unknown unknowns . In Thirty-Second AAAI Conference on Artificial Intelligence. Gagan Bansal and Daniel S Weld. 2018. A coverage-based utility model for identifying unknown unknowns. In Thirty-Second AAAI Conference on Artificial Intelligence.
- 10.1609/hcomp.v1i1.13091 · DOI · Paper page
- 10.1145/2470654.2466265 · DOI · Paper page
- 10.1145/2556288.2557011 · DOI · Paper page
- 10.1016/j.procs.2012.04.177 · DOI
- Alec Go , Richa Bhayani , and Lei Huang . 2009. Twitter sentiment classification using distant supervision. CS224N Project Report , Stanford 1, 12 ( 2009 ). Alec Go, Richa Bhayani, and Lei Huang. 2009. Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford 1, 12 (2009).
- 10.1145/2872427.2883037 · DOI · Paper page
- 10.18653/v1/N18-2099 · DOI
- Himabindu Lakkaraju , Ece Kamar , Rich Caruana , and Eric Horvitz . 2017 . Identifying unknown unknowns in the open world: Representations and policies for guided exploration . In Thirty-First AAAI Conference on Artificial Intelligence. Himabindu Lakkaraju, Ece Kamar, Rich Caruana, and Eric Horvitz. 2017. Identifying unknown unknowns in the open world: Representations and policies for guided exploration. In Thirty-First AAAI Conference on Artificial Intelligence.
- 10.5555/3091622.3091662 · doi:10.5555/3091622.3091662
- 10.1145/2702123.2702416 · DOI
- Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , and Rob Fergus . 2014 . Intriguing properties of neural networks . In International Conference on Learning Representations. http://arxiv.org/abs/1312 .6199 Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In International Conference on Learning Representations. http://arxiv.org/abs/1312.6199 · arXiv
- Omar F Zaidan and Chris Callison-Burch . 2011 . Crowdsourcing translation: Professional quality from non-professionals . In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. 1220–1229 . Omar F Zaidan and Chris Callison-Burch. 2011. Crowdsourcing translation: Professional quality from non-professionals. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. 1220–1229.
Cited by
Walmsley, M., Lintott, C., Géron, T., Kruk, S., Krawczyk, C., Willett, K. W., Bamford, S., Kelvin, L. S., Fortson, L., Gal, Y., et al. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab2093 · Cited by 197
Shen, H., DeVos, A., Eslami, M., & Holstein, K. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479577 · Cited by 171
“, [6, 58, 61, 66, 89]), which automatically surface cases that are more likely to be mislabeled and/or misclassified.”
BackgroundImproving Human-AI Collaboration With Descriptions of AI Behavior
Cabrera, Á. A., Perer, A., & Hong, J. I. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579612 · Cited by 87
“More recently, crowd-based systems such as Pandora [44], Deblinder [9], and P-BTM [38] have shown how crowdsourcing can augment behavioral analysis tools by surfacing previously unknown model failures.”
BackgroundA multifaceted vision of the human-AI collaboration: a comprehensive review
Puerta-Beldarrain, M., Gómez-Carmona, O., Sánchez-Corcuera, R., Casado-Mansilla, D., López-de-Ipiña, D., & Chen, L. (2025) · IEEE Access · doi:10.1109/access.2025.3536095 · Cited by 73
“For instance, Liu et al. utilized non-experts to label system classification outputs and identify unknown-unknowns , learning from them to enhance initial classification [199].”
Extending a Human-AI Collaboration Framework with Dynamism and Sociality
Muller, M., & Weisz, J. (2022) · 2022 Symposium on Human-Computer Interaction for Work · doi:10.1145/3533406.3533407 · Cited by 37
Metadata
- Authors
- Liu, A., Guerra, S., Fung, I., Matute, G., Kamar, E., & Lasecki, W.
- Venue
- Proceedings of The Web Conference 2020
- Publisher
- ACM
- Published
- 2020-04-20
- Pages
- 2432-2442
- OpenAlex
- W3012736183
- Cited by
- 31
- References
- 5
- FWCI
- 2.22
- Type
- conference paper
- Language
- en
- Open access
- gold
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.