The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
HateCheck: Functional Tests for Hate Speech Detection Models
Open accessAbstract
Detecting online hate is a difficult task that even state-of-the-art models struggle with. Typically, hate speech detection models are evaluated by measuring their performance on held-out test data using metrics such as accuracy and F1 score. However, this approach makes it difficult to identify specific model weak points. It also risks overestimating generalisable model performance due to increasingly well-evidenced systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, we introduce HateCheck, a suite of functional tests for hate speech detection models. We specify 29 model functionalities motivated by a review of previous research and a series of interviews with civil society stakeholders. We craft test cases for each functionality and validate their quality through a structured annotation process. To illustrate HateCheck's utility, we test near-state-of-the-art transformer models as well as two popular commercial models, revealing critical model weaknesses.
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
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Grounded theory research: Procedures, canons, and evaluative criteria
Corbin, J. M., & Strauss, A. (1990) · Qualitative Sociology · doi:10.1007/bf00988593 · Cited by 11,133
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359
Transformers: 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
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
Automated Hate Speech Detection and the Problem of Offensive Language
Davidson, T., Warmsley, D., Macy, M., & Weber, I. (2017) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v11i1.14955 · Cited by 2,610
Grounded Theory Research: Procedures, Canons, and Evaluative Criteria
Corbin, J., & Strauss, A. (1990) · Zeitschrift fur Soziologie · doi:10.1515/zfsoz-1990-0602 · Cited by 1,710 · cited 1×
“Using a grounded theory approach (Corbin and Strauss, 1990), we identified”
MethodA Survey on Automatic Detection of Hate Speech in Text
Fortuna, P., & Nunes, S. (2019) · ACM Computing Surveys · doi:10.1145/3232676 · Cited by 1,241 · cited 1×
“tified linguistic challenges in hate speech detection from review articles and commentaries (e.g. Schmidt and Wiegand, 2017; Fortuna and Nunes, 2018; Vidgen et al., 2019).”
BackgroundBeyond accuracy: behavioral testing of NLP models with CheckList
Ribeiro, M. T., Wu, T., Guestrin, C., & Singh, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.442 · Cited by 890
Bender, E. M., & Friedman, B. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00041 · Cited by 854 · cited 1×
“Following Bender and Friedman (2018), we provide a data statement, which documents the generation and provenance of test cases in H ATE C HECK .”
MethodThe Risk of Racial Bias in Hate Speech Detection
Sap, M., Card, D., Gabriel, S., Choi, Y., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1163 · Cited by 817
Measuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674
Adversarial NLI: A New Benchmark for Natural Language Understanding
Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., & Kiela, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.441 · Cited by 656
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models
Ettinger, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00298 · Cited by 511
A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media
Mozafari, M., Farahbakhsh, R., & Crespi, N. (2020) · Studies in Computational Intelligence · doi:10.1007/978-3-030-36687-2_77 · Cited by 396
Probing Neural Network Comprehension of Natural Language Arguments
Niven, T., & Kao, H.-Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1459 · Cited by 395 · cited 1×
“…if there are systematic gaps and biases in training data, models may perform deceptively well on corresponding held-out test sets by learning simple decision rules rather than encoding a more generalisable understanding of the task (e.g. Niven and Kao, 2019; Geva et al., 2019; Shah et al., 2020).”
MethodThe hateful memes challenge: Detecting hate speech in multimodal memes
Kiela, D., Firooz, H., Mohan, A., Goswami, V., Singh, A., Ringshia, P., & Testuggine, D. (2020) · arXiv · doi:10.48550/arxiv.2005.04790 · Cited by 352 · cited 1×
“and multimodal content, such as images combined with text, are common on social media and constitute a current research frontier in hate speech detection (Vidgen et al., 2019; Kiela et al., 2020).”
BackgroundTargeted Syntactic Evaluation of Language Models
Marvin, R., & Linzen, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1151 · Cited by 334
Reducing Gender Bias in Abusive Language Detection
Park, J. H., Shin, J., & Fung, P. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1302 · Cited by 323 · cited 3×
“Corre-spondingly, models trained on such datasets have been shown to be overly sensitive to lexical features such as group identifiers (Park et al., 2018; Dixon et al., 2018; Kennedy et al., 2020), and to generalise poorly to other datasets (Nejadgholi and Kiritchenko, 2020; Samory et al., 2020).”
BackgroundMethodBreaking NLI Systems with Sentences that Require Simple Lexical Inferences
Glockner, M., Shwartz, V., & Goldberg, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2103 · Cited by 319
Geva, M., Goldberg, Y., & Berant, J. (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/d19-1107 · Cited by 284
Dynabench: Rethinking Benchmarking in NLP
Kiela, D., Bartolo, M., Nie, Y., Kaushik, D., Geiger, A., Wu, Z., Vidgen, B., Prasad, G., Singh, A., Ringshia, P., et al. (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.324 · Cited by 254
Self-citationPredictive biases in natural language processing models: A conceptual framework and overview
Shah, D. S., Schwartz, H. A., & Hovy, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.468 · Cited by 241
Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack
Dinan, E., Humeau, S., Chintagunta, B., & Weston, J. (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/d19-1461 · Cited by 161
Detecting the Hate Code on Social Media
Magu, R., Joshi, K., & Luo, J. (2017) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v11i1.14921 · Cited by 93
Cited by
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
“We note that we are subject to the social bias of the Perspective API, which can assign higher toxicity to innocuous mentions of certain identity groups (Dixon et al., 2018; Röttger et al., 2021).”
BackgroundRed Teaming Language Models with Language Models
Perez, E., Huang, S., Song, F., Cai, T., Ring, R., Aslanides, J., Glaese, A., McAleese, N., & Irving, G. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.225 · Cited by 363
Auditing large language models: a three-layered approach
Mökander, J., Schuett, J., Kirk, H. R., & Floridi, L. (2024) · AI and Ethics · doi:10.1007/s43681-023-00289-2 · Cited by 289
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Hartvigsen, T., Gabriel, S., Palangi, H., Sap, M., Ray, D., & Kamar, E. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.234 · Cited by 279
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Hartvigsen, T., Gabriel, S., Palangi, H., Sap, M., Ray, D., & Kamar, E. (2022) · arXiv · doi:10.48550/arxiv.2203.09509 · Cited by 276
Metadata
- Authors
- Röttger, P., Vidgen, B., Nguyen, D., Waseem, Z., Margetts, H., & Pierrehumbert, J.
- Venue
- 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)
- Published
- 2021
- Pages
- 41-58
- ISSN
- 2331-8422 (ISSN-L)
- OpenAlex
- W3175487198
- Cited by
- 187
- References
- 26
- Type
- posted content
- 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.