The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
Open accessAbstract
Su Lin Blodgett, Gilsinia Lopez, Alexandra Olteanu, Robert Sim, Hanna Wallach. 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). 2021.
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?
Group-specific bias benchmarks are time-consuming to develop and utilize, and the overall field lacks measurement validity and theoretical grounding.
“Evaluating the expanding capabilities of LLMs is a complex research area28,29, with group-specific bias benchmarks shown to be time-consuming to develop and utilize30–33, and the overall field lacking measurement validity and theoretical grounding30,34.”
From Generative language models exhibit social identity biases (2024) · cites this paper as [34]
The Conclusion (§7; page not specified) identifies unclear conceptualization and threats to measurement validity in the stereotyping benchmarks studied, but does not establish that the overall field lacks theoretical grounding or measurement validity. The Discussion (§6; page not specified) calls an expert-involved development process “admittedly longer”; it does not show that group-specific bias benchmarks generally take a long time to develop and utilize. (LLM, conf=0.84)
Experimental — accuracy not yet measuredMany bias and fairness approaches assume some implicitly desirable criterion but do not explicitly acknowledge or state the normative social values that justify their framework.
“Many approaches, for instance, assume some implicitly desirable criterion ( e.g. , a model output should be independent of any social group in the input), but do not explicitly acknowledge or state the normative social values that justify their framework.”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. 2021
Section 2.3 describes assumptions about ideal model behavior, including equal probabilities for sentences about different target groups. Section 6 says the benchmarks make implicit decisions about stereotyping that are not explicitly discussed or justified. The paper examines four stereotyping benchmarks, however, rather than establishing this claim about many bias and fairness approaches generally or specifically about their normative social values. (LLM, conf=0.84)
Experimental — accuracy not yet measuredIn nearly half of all instances, these datasets contain ambiguities about what stereotypes they capture, raising questions whether they are valid indicators of real-world stereotypes at all.
“In nearly half of all instances, these datasets contain ambiguities about what stereotypes they capture, raising questions whether they are valid indicators of real-world stereotypes at all.”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. (2021)
The paper’s overview reports ambiguities about stereotyping and questions whether the benchmarks measure it effectively; §4.2.2 also describes threats to validity. But its figure is that 0%–58% of sampled tests across the benchmarks were free of *any* identified pitfall, not that nearly half of all instances were ambiguous about which stereotypes they capture (overview and Basic Statistics; page numbers unavailable). (LLM, conf=0.88)
Experimental — accuracy not yet measuredSeveral widely-used evaluation datasets suffer from reliability and validity issues, including ambiguities about whether instances accurately reflect real-world stereotypes, inconsistent treatment of social groups, assumptions of near-perfect understanding of language, and lack of syntactic and semantic diversity.
“several widely-used evaluation datasets suffer from reliability and validity issues, including ambiguities about whether instances accurately reflect real-world stereotypes, inconsistent treatment of social groups, assumptions of near-perfect understanding of language, and lack of syntactic and semantic diversity (Blodgett et al. 2021; Gupta et al. 2023; Selvam et al. 2023).”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. 2021
Sections 4.2.2 and 5.1 identify tests that do not clearly capture stereotypes, unnatural text, incommensurable groups, and inconsistent labeling of race and nationality; §4.2.1 also identifies consistency problems within sentence pairs. These support the validity concerns, but the passages do not establish assumptions of near-perfect language understanding or a lack of syntactic and semantic diversity. The paper discusses syntax inconsistencies within pairs, which is a different issue. (LLM, conf=0.86)
Experimental — accuracy not yet measuredBlodgett et al. (2021) highlight several severe shortcomings of Winogender, WinoBias, StereoSet, and CrowS-Pairs.
“Blodgett et al. (2021) highlight several severe shortcomings of several counterfactual input datasets, namely Winogender, WinoBias, StereoSet, and CrowS-Pairs.”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. (2021)
At the core of these issues are unclear articulation of the power imbalances, harm, or other stereotype content present in each instance, and inconsistent, invalid, or unrelated perturbations of social groups.
“At the core of these issues are (1) unclear articulation of the power imbalances, harm, or other stereotype content present in each instance; and (2) inconsistent, invalid, or unrelated perturbations of social groups.”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. (2021)
These prompting datasets also suffer from some data reliability issues, but to a lesser extent than those discussed in Blodgett et al. (2021).
“These datasets also suffer from some data reliability issues, but to a lesser extent than those discussed in Blodgett et al. (2021) (Liang et al. 2022).”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Blodgett et al. (2021)
Prompt-based learning with GPT-3 has achieved very strong performances in zero-shot and one-shot settings, without any fine-tuning.
“In addition, prompt-based learning with GPT-3 has achieved very strong performances in zero-shot and one-shot settings (i.e. with only zero or one labelled example), without any fine-tuning [7].”
From GPT-3-Driven Pedagogical Agents to Train Children’s Curious Question-Asking Skills (2024) · cites this paper as [7]
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
Austin, J. L. (1975) · doi:10.1093/acprof:oso/9780198245537.001.0001 · Cited by 21,496
Black Feminist Thought: Knowledge, Consciousness, and the Politics of Empowerment.
Brewer, R. M., & Collins, P. H. (1992) · Contemporary Sociology · doi:10.2307/2074808 · Cited by 19,445
A General Inductive Approach for Analyzing Qualitative Evaluation Data
Thomas, D. R. (2006) · American Journal of Evaluation · doi:10.1177/1098214005283748 · Cited by 10,858 · cited 2×
“This inductive approach aligns with our exploratory goal of surfacing a range of pitfalls, including many that are not on the community radar and thus likely to be overlooked by a more deductive approach requiring a predefined codebook grounded in existing assumptions (Thomas, 2006).”
MethodClark, H. H. (1996) · doi:10.1017/cbo9780511620539 · Cited by 5,123
Glick, P., & Fiske, S. T. (2001) · American Psychologist · doi:10.1037/0003-066x.56.2.109 · Cited by 2,224
Measurement Validity: A Shared Standard for Qualitative and Quantitative Research
Adcock, R., & Collier, D. (2001) · American Political Science Review · doi:10.1017/s0003055401003100 · Cited by 1,639
Measurement Validity: A Shared Standard for Qualitative and Quantitative Research
Collier, D., & Adcock, R. (2001) · eScholarship (California Digital Library) · Cited by 1,603
Bucholtz, M., & Hall, K. (2005) · Wiley eBooks · doi:10.1002/9780470996522.ch16 · Cited by 1,153
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051 · cited 2×
“Yet even as such benchmarks are added to popular NLP leaderboards like Super-Glue (Wang et al., 2019), whether these they actually help measure the extent to which NLP systems produce computational harms remains unknown.”
BackgroundLanguage (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 1×
“, 2020), and a lack of consensus about how to conceptualize or operationalize such harms (Blodgett et al., 2020; Jacobs and Wallach, 2021).”
BackgroundSelf-citationThe psychology of stereotyping
(2004) · Choice Reviews Online · doi:10.5860/choice.42-1892 · Cited by 751 · cited 1×
“which groups to consider or which aspects of stereotyping to focus on, including occupations, physical features, emotional traits, or language use (Schneider, 2005).”
BackgroundRealToxicityPrompts: 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
Gender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2003 · Cited by 684 · cited 5×
“These datasets consist of tests that can take a variety of formats, including sentence templates where terms pertaining to groups or their attributes are perturbed (Rudinger et al., 2018; Zhao et al., 2018; Kurita et al., 2019), prompts designed to elicit problematic responses (Gehman et al.”
BackgroundInfluentialHow to analyze political attention with minimal assumptions and costs
Quinn, K. M., Monroe, B. L., Colaresi, M., Crespin, M. H., & Radev, D. R. (2010) · American Journal of Political Science · doi:10.1111/j.1540-5907.2009.00427.x · Cited by 671 · cited 1×
“Measurement Modeling We apply a measurement modeling lens by viewing each benchmark as a measurement model (MM) (e.g., Quinn et al., 2010; Jacobs and Wallach, 2021).”
MethodStereoSet: 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 · cited 8×
“Consider the illustrative example about “Norwe-gian salmon” in Figure 1—drawn from an existing benchmark (Nadeem et al., 2020)—which depicts a test meant (according to the metadata) to capture a stereotype about race.”
BackgroundMethodInfluentialStereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2020) · arXiv · doi:10.48550/arxiv.2004.09456 · Cited by 643
Data and its (dis)contents: A survey of dataset development and use in machine learning research
Paullada, A., Raji, I. D., Bender, E. M., Denton, E., & Hanna, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100336 · Cited by 548 · cited 1×
“Therefore, it is critical to uncover the explicit and implicit assumptions that these benchmarks carry and the incentives to which they may give rise (Paullada et al., 2020).”
BackgroundThe Woman Worked as a Babysitter: On Biases in Language Generation
Sheng, E., Chang, K.-W., Natarajan, P., & Peng, N. (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/d19-1339 · Cited by 537 · cited 1×
“…sentence templates where terms pertaining to groups or their attributes are perturbed (Rudinger et al., 2018; Zhao et al., 2018; Kurita et al., 2019), prompts designed to elicit problematic responses (Gehman et al., 2020; Sheng et al., 2019; Example Sentences Context I really like Norweigan salmon.”
BackgroundPersistent Anti-Muslim Bias in Large Language Models
Abid, A., Farooqi, M., & Zou, J. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462624 · Cited by 476 · cited 2×
“…due in no small part to the deeply contextual and open nature of language use and tasks (Austin, 1975; Clark, 1996; Howcroft et al., 2020; Abid et al., 2021; Olteanu et al., 2020), and a lack of consensus about how to conceptualize or operationalize such harms (Blod-gett et al., 2020;…”
BackgroundReskin, B. F. (1988) · Gender & Society · doi:10.1177/089124388002001005 · Cited by 468
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Nangia, N., Vania, C., Bhalerao, R., & Bowman, S. R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.154 · Cited by 446
Gender Bias in Coreference Resolution
Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2002 · Cited by 443 · cited 5×
“These datasets consist of tests that can take a variety of formats, including sentence templates where terms pertaining to groups or their attributes are perturbed (Rudinger et al., 2018; Zhao et al., 2018; Kurita et al., 2019), prompts designed to elicit problematic responses (Gehman et al.”
BackgroundInfluentialJacobs, A. Z., & Wallach, H. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445901 · Cited by 362 · cited 3×
“Measurement Modeling We apply a measurement modeling lens by viewing each benchmark as a measurement model (MM) (e.g., Quinn et al., 2010; Jacobs and Wallach, 2021).”
BackgroundMethodSelf-citationMeasuring Bias in Contextualized Word Representations
Kurita, K., Vyas, N., Pareek, A., Black, A. W., & Tsvetkov, Y. (2019) · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · doi:10.18653/v1/w19-3823 · Cited by 348 · cited 2×
“…formats, including sentence templates where terms pertaining to groups or their attributes are perturbed (Rudinger et al., 2018; Zhao et al., 2018; Kurita et al., 2019), prompts designed to elicit problematic responses (Gehman et al., 2020; Sheng et al., 2019; Example Sentences Context I really…”
BackgroundHowcroft, D. M., Belz, A., Clinciu, M., Gkatzia, D., Hasan, S. A., Mahamood, S., Mille, S., van Miltenburg, E., Santhanam, S., & Rieser, V. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.23 · Cited by 292
Perturbation Sensitivity Analysis to Detect Unintended Model Biases
Prabhakaran, V., Hutchinson, B., & Mitchell, M. (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/d19-1578 · Cited by 115 · cited 2×
“Names have been used as demographic proxies in both social computing and NLP work, and often appear in close proximity to other demographic markers in text corpora; LMs might thus memorize incidental associations between names and demographic criteria (Prabhakaran et al., 2019; Shwartz et al., 2020).”
BackgroundMethodInvestigating African-American Vernacular English in Transformer-Based Text Generation
Groenwold, S., Ou, L., Parekh, A., Honnavalli, S., Levy, S., Mirza, D., & Wang, W. Y. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.473 · Cited by 59
“You are grounded!”: Latent Name Artifacts in Pre-trained Language Models
Shwartz, V., Rudinger, R., & Tafjord, O. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.556 · Cited by 51
When Are Search Completion Suggestions Problematic?
Olteanu, A., Díaz, F., & Kazai, G. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415242 · Cited by 38 · cited 2×
“Auditing NLP systems for computational harms like the reproduction of stereotypes or hate speech remains a persistent challenge, due in no small part to the deeply contextual and open nature of language use and tasks (Austin, 1975; Clark, 1996; Howcroft et al., 2020; Abid et al., 2021; Olteanu et al., 2020), and a lac…”
BackgroundSelf-citationOvercoming Failures of Imagination in AI Infused System Development and DeploymentPreprint
Boyarskaya, M., Olteanu, A., & Crawford, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13416 · Cited by 21 · cited 2×
“…modeling framework can provide analytical clarity and a scaffold for future work in this direction. be inherently beneficial with little to no potential for harm, and thus often (paradoxically) fails to examine its limitations or possible unintended negative consequences (Boyarskaya et al., 2020).”
BackgroundSelf-citationPersistent Anti-Muslim Bias in Large Language ModelsPreprint
Abid, A., Farooqi, M., & Zou, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05783 · Cited by 17
Data and its (dis)contents: A survey of dataset development and use in machine learning research
Paullada, A., Raji, I. D., Bender, E. M., Denton, E., & Hanna, A. (2020) · arXiv · doi:10.48550/arxiv.2012.05345
Flagged first, then by citations
Research works printed but not linked: 1
- David J. Schneider. 2005. The Psychology of Stereotyp- ing. Guilford Press.
Cited by
Sorted by citations
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
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
“…et al., 2021b), there is a lack of standardization of fairness benchmarks, an understanding of what harms different bias measures in NLP relate to (Blodgett et al., 2020, 2021; Jacobs & Wallach, 2021), and coverage of identities in fluid, comprehensive ways (Cao & Daumé III, 2020; Dev et al.,…”
BackgroundGemini: A Family of Highly Capable Multimodal Models
Gemini Team, Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.11805 · Cited by 990
Bias and Fairness in Large Language Models: A Survey
Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., Yu, T., Zhang, R., & Ahmed, N. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00524 · Cited by 1,245
“Others lack consistency in their definitions of bias, or do not seriously engage with the relevant power dynamics that perpetuate the underlying harm (Blodgett et al., 2021).”
BackgroundEthical and social risks of harm from Language Models
Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., Kasirzadeh, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04359 · Cited by 477
Gender bias and stereotypes in Large Language Models
Kotek, H., Dockum, R., & Sun, D. (2023) · Proceedings of The ACM Collective Intelligence Conference · doi:10.1145/3582269.3615599 · Cited by 381
“However, as is well known, language models perpetuate and occasionally amplify biases, stereotypes, and negative perceptions of minoritized groups in society [10, 13, 14, 66, 69, 84, 85, 90].”
BackgroundBBQ: A hand-built bias benchmark for question answering
Parrish, A., Chen, A., Nangia, N., Padmakumar, V., Phang, J., Thompson, J., Htut, P. M., & Bowman, S. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.165 · Cited by 186
Harms from Increasingly Agentic Algorithmic Systems
Chan, A., Salganik, R., Markelius, A., Pang, C., Rajkumar, N., Krasheninnikov, D., Langosco, L., He, Z., Duan, Y., Carroll, M., et al. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594033 · Cited by 149
“While it is crucial not to idealize or over-hype a model’s performance by ignoring model failures [23, 24, 28, 47, 120, 153, 187], it is also important not to understate (and thus fail to anticipate negative consequences of) what these models can do and may be capable of doing in the near future [31, 90, 103], especia…”
BackgroundIn Conversation with Artificial Intelligence: Aligning language Models with Human Values
Kasirzadeh, A., & Gabriel, I. (2023) · Philosophy & Technology · doi:10.1007/s13347-023-00606-x · Cited by 127
“3 However, early instances of these models also present a number of risks and possible failure modes, including the production of false, offensive, or irrelevant information that could lead to a range of harms [15, 50, 104].”
BackgroundGPT-3-Driven Pedagogical Agents to Train Children’s Curious Question-Asking Skills
Abdelghani, R., Wang, Y.-H., Yuan, X., Wang, T., Lucas, P., Sauzéon, H., & Oudeyer, P.-Y. (2024) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-023-00340-7 · Cited by 129
“Indeed, despite the impressive advances, LLMs are still considered as ’black-box’ systems that are impossible for us to control and that can generate stereotypes and wrong/ biased content [4, 7].”
Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models
Cheng, M., Durmus, E., & Jurafsky, D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.84 · Cited by 228
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Meade, N., Poole-Dayan, E., & Reddy, S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.132 · Cited by 135
Measuring algorithmically infused societies
Wagner, C., Strohmaier, M., Olteanu, A., Kıcıman, E., Contractor, N., & Eliassi-Rad, T. (2021) · Nature · doi:10.1038/s41586-021-03666-1 · Cited by 144
“Although the Common Task Framework (CTF) has successfully driven progress in some areas of machine learning 68 , the ‘leaderboardism’ in science has also led to the quick development of mis-or under-specified benchmark datasets and shared tasks 69,70 .”
BackgroundInfluentialSelf-citationA toolbox for surfacing health equity harms and biases in large language models
Pfohl, S. R., Cole-Lewis, H., Sayres, R., Neal, D., Asiedu, M., Dieng, A., Tomasev, N., Rashid, Q. M., Azizi, S., Rostamzadeh, N., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03258-2 · Cited by 113
Explicitly unbiased large language models still form biased associations
Bai, X., Wang, A., Sucholutsky, I., & Griffiths, T. L. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2416228122 · Cited by 300
Pellert, M., Lechner, C. M., Wagner, C., Rammstedt, B., & Strohmaier, M. (2024) · Perspectives on Psychological Science · doi:10.1177/17456916231214460 · Cited by 97
“The problems arising from the ad hoc quality of many of such tests have been pointed out (Blodgett et al., 2021).”
Designing Responsible AI: Adaptations of UX Practice to Meet Responsible AI Challenges
Wang, Q., Madaio, M., Kane, S. K., Kapania, S., Terry, M. A., & Wilcox, L. G. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581278 · Cited by 110
“intentionally generate harmful outputs (so they can be prevented) often come with pitfalls that render these methods invalid [14].”
BackgroundGenerative language models exhibit social identity biases
Hu, T., Kyrychenko, Y., Rathje, S., Collier, N., van der Linden, S., & Roozenbeek, J. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00741-1 · Cited by 100
“GPT-2-Large Positive .5106 .9375 2 Results”
A Survey of Race, Racism, and Anti-Racism in NLP
Field, A., Blodgett, S. L., Talat, Z., & Tsvetkov, Y. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.149 · Cited by 113
“More work is needed to understand any privacy concerns and the strengths and limitations of these data (Blodgett et al., 2021).”
BackgroundSelf-citationCollective Constitutional AI: Aligning a Language Model with Public Input
Huang, S., Siddarth, D., Lovitt, L., Liao, T. I., Durmus, E., Tamkin, A., & Ganguli, D. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658979 · Cited by 79
“Automated metrics may fail to capture the intended harm, for which NLP bias benchmarks have been criticized [13, 14]).”
BackgroundOn Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Shaikh, O., Zhang, H., Held, W., Bernstein, M., & Yang, D. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.244 · Cited by 76
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Shaikh, O., Zhang, H., Held, W., Bernstein, M., & Yang, D. (2022) · arXiv · doi:10.48550/arxiv.2212.08061 · Cited by 76
“Bench-marks often-time have differing conceptualizations of bias (Blodgett et al., 2021), leading to contra-dictory results (Delobelle et al., 2022; Cao et al., 2022; Goldfarb-Tarrant et al., 2021).”
BackgroundPerturbation augmentation for fairer NLP
Qian, R., Ross, C., Fernandes, J., Smith, E. M., Kiela, D., & Williams, A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.646 · Cited by 69
You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings
Talat, Z., Névéol, A., Biderman, S., Clinciu, M., Dey, M., Longpre, S., Luccioni, A. S., Masoud, M., Mitchell, M., Radev, D., et al. (2022) · doi:10.18653/v1/2022.bigscience-1.3 · Cited by 74
“According to Jacobs and Wallach (2021) and Blodgett et al. (2021), bias mea-452 sures are measurement models which link observable properties, e.g., quality-of-service and representational biases, with unobservable theoretical constructs such as social discrimination, power dynamics, and systemic…”
BackgroundDelobelle, P., Tokpo, E., Calders, T., & Berendt, B. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.122 · Cited by 57
“However, other measures, like CrowS-pairs (Nangia et al., 2020), correlate less with two extrinsic measures, which we suspect to be related to issues found by Blodgett et al. (2021), although more experiments are needed to confirm this.”
BackgroundResultInfluentialUnmasking the Mask – Evaluating Social Biases in Masked Language Models
Kaneko, M., & Bollegala, D. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i11.21453 · Cited by 60
Mitigating Language-Dependent Ethnic Bias in BERT
Ahn, J., & Oh, A. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.42 · Cited by 64
Unlearning Bias in Language Models by Partitioning Gradients
Yu, C., Jeoung, S., Kasi, A., Yu, P., & Ji, H. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.375 · Cited by 61
“We acknowledge that the StereoSet and CrowS datasets and metrics are not ideal evaluation measures for debiasing work (see Blodgett et al. (2021) for more details about their pitfalls).”
BackgroundCao, Y., Pruksachatkun, Y., Chang, K.-W., Gupta, R., Kumar, V., Dhamala, J., & Galstyan, A. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-short.62 · Cited by 70
Mirowski, P., Love, J., Mathewson, K., & Mohamed, S. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658993 · Cited by 37
Névéol, A., Dupont, Y., Bezançon, J., & Fort, K. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.583 · Cited by 38
“During the translation process, we identified issues with the original CrowS-pairs content, including some described in Blodgett et al. (2021).”
BackgroundMethodFairness in Language Models Beyond English: Gaps and Challenges
Ramesh, K., Sitaram, S., & Choudhury, M. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.157 · Cited by 60
Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation
Eriksson, M., Purificato, E., Noroozian, A., Vinagre, J., Chaslot, G., Gomez, E., & Fernandez-Llorca, D. (2025) · arXiv · doi:10.48550/arxiv.2502.06559 · Cited by 35
“In a close analysis of four benchmarks used to evaluate fairness in natu-ral language processing (StereoSet, CrowS-Pairs, WinoBias, and WinoGender), Blodgett et al. (2021) for example found that all benchmarks revealed severe weaknesses in terms of defining what is being measured.”
Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs
Rao, A., Khandelwal, A., Tanmay, K., Agarwal, U., & Choudhury, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.892 · Cited by 78
Pipelines for Social Bias Testing of Large Language Models
Nozza, D., Bianchi, F., & Hovy, D. (2022) · doi:10.18653/v1/2022.bigscience-1.6 · Cited by 33
“Blodgett et al. (2021) presented a critical review of some social bias tests and found significant issues with noise, unnaturalness, and reliability of the some work (Nangia et al., 2020; Nadeem et al., 2021).”
BackgroundGender Bias in Masked Language Models for Multiple Languages
Kaneko, M., Imankulova, A., Bollegala, D., & Okazaki, N. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.197 · Cited by 35
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Gupta, U., Dhamala, J., Kumar, V., Verma, A., Pruksachatkun, Y., Krishna, S., Gupta, R., Chang, K.-W., Steeg, G. V., & Galstyan, A. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.55 · Cited by 38
Responsible Language Technologies: Foreseeing and Mitigating Harms
Blodgett, S. L., Liao, Q. V., Olteanu, A., Mihalcea, R. F., Muller, M. J., Scheuerman, M. K., Tan, C., & Yang, Q. (2022) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3491101.3516502 · Cited by 25
“Computationally, such harms might occur not only due to what data NLP models are being trained on, but also due to how that data might be embedded and represented by these NLP models and the systems they power, or even due to how NLP systems are often being evaluated [6, 16, 17].”
BackgroundSelf-citationSwahBERT: Language Model of Swahili
Martin, G. L., Mswahili, M. E., Jeong, Y.-S., & Young-Seob, J. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.23 · Cited by 30
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models
Cao, Y., Sotnikova, A., Daumé, H., Rudinger, R., & Zou, L. X. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.92 · Cited by 28
An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models
Xie, Z., & Lukasiewicz, T. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.876 · Cited by 41
MABEL: Attenuating Gender Bias using Textual Entailment Data
He, J., Xia, M., Fellbaum, C., & Chen, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.657 · Cited by 39
Fairness-Aware Structured Pruning in Transformers
Zayed, A., Mordido, G., Shabanian, S., Baldini, I., & Chandar, S. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30256 · Cited by 25
Examining risks of racial biases in NLP tools for child protective services
Field, A., Coston, A., Gandhi, N., Chouldechova, A., Putnam-Hornstein, E., Steier, D., & Tsvetkov, Y. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594094 · Cited by 18
“Curated data sets facilitate reproducibility and controlled experiments, but they can fail to articulate what is being measured, contain ambiguities, and may not reflect real deployment settings [2].”
BackgroundInterpreting Gender Bias in Neural Machine Translation: Multilingual Architecture Matters
Costa‐jussà, M. R., Escolano, C., Basta, C., Ferrando, J., Batlle, R., & Kharitonova, K. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i11.21442 · Cited by 22
“Recently, Blodgett et al. (2021) pointed out the downsides of this benchmark, including unnaturalness and logical failures, among others.”
BackgroundRepresentation in AI Evaluations
Bergman, A. S., Hendricks, L. A., Rauh, M., Wú, B., Agnew, W. S., Kunesch, M., Duan, I., Gabriel, I., & Isaac, W. S. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594019 · Cited by 20
“Representational biases arise when a system ( e.g. a search engine or a generative AI) represents some social groups in a less favorable light than others, demeans them ( e.g. [59, 87]), or fails to recognise their existence altogether [2, 18, 19, 33, 72, 133, 143].”
BackgroundBenchmark suites instead of leaderboards for evaluating AI fairness
Wang, A., Hertzmann, A., & Russakovsky, O. (2024) · Patterns · doi:10.1016/j.patter.2024.101080 · Cited by 19
“12 They rightly point out that different harms cannot be meaningfully averaged into a single score, and moreover, benchmark optimization encourages THE BIGGER PICTURE As artificial intelligence (AI) systems become increasingly complex and ubiquitous, developers and users need to understand these…”
Gender Bias in Natural Language Processing and Computer Vision: A Comparative Survey
Bartl, M., Mandal, A., Leavy, S., & Little, S. (2024) · ACM Computing Surveys · doi:10.1145/3700438 · Cited by 23
“In addition to inconsistencies in their application, Blodgett et al. [18] moreover found that a variety of pitfalls in four bias measuring datasets themselves.”
InfluentialDeconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications
Zhou, K., Blodgett, S. L., Trischler, A., Daumé, H., Suleman, K., & Olteanu, A. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.24 · Cited by 23
Self-citationPellert, M., Lechner, C. M., Wagner, C., Rammstedt, B., & Strohmaier, M. (2022) · doi:10.31234/osf.io/jv5dt · Cited by 16
In conversation with Artificial Intelligence: aligning language models with human values
Kasirzadeh, A., & Gabriel, I. (2022) · arXiv · doi:10.48550/arxiv.2209.00731 · Cited by 128
“3 However, early instances of these models also present a number of risks and possible failure modes, including the production of false, offensive, or irrelevant information that could lead to a range of harms [15, 50, 104].”
BackgroundSeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models
Jha, A., Davani, A. M., Reddy, C. K. A., Dave, S., Prabhakaran, V., & Dev, S. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.548 · Cited by 43
A comparative study on the impact of model compression techniques on fairness in language models
Ramesh, K., Chavan, A., Pandit, S., & Sitaram, S. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.878 · Cited by 15
Detecting Unintended Social Bias in Toxic Language Datasets
Sahoo, N., Gupta, H., & Bhattacharyya, P. (2022) · Conference on Computational Natural Language Learning · doi:10.18653/v1/2022.conll-1.10 · Cited by 25
Li, Y., Du, M., Song, R., Wang, X., Sun, M., & Wang, Y. (2024) · Artificial Intelligence · doi:10.1016/j.artint.2024.104143 · Cited by 16
A Robust Bias Mitigation Procedure Based on the Stereotype Content Model
Ungless, E. L., Rafferty, A., Nag, H., & Roß, B. (2022) · Workshop on Natural Language Processing and Computational Social Science (NLP+CSS) · doi:10.18653/v1/2022.nlpcss-1.23 · Cited by 16
Debiasing pretrained text encoders by paying attention to paying attention
Gaci, Y., Benatallah, B., Casati, F., & Benabdeslem, K. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.651 · Cited by 14
“We acknowledge that intrinsic metrics have recently been criticized (GoldfarbTarrant et al., 2020; Aribandi et al., 2021; Blodgett et al., 2021).”
BackgroundMetaethical perspectives on ‘benchmarking’ AI ethics
LaCroix, T., & Luccioni, A. S. (2025) · AI and Ethics · doi:10.1007/s43681-025-00703-x · Cited by 27
“, 2020)) to embedded gender and cultural stereotypes in common NLP benchmarks (Blodgett et al., 2021).”
Undesirable Biases in NLP: Addressing Challenges of Measurement
van der Wal, O., Bachmann, D., Leidinger, A., van Maanen, L., Zuidema, W. H., & Schulz, K. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15195 · Cited by 28
“…for testing the validity of bias measures include, for example, assessing whether operationalizations are consistent with the underlying theory (Blodgett et al., 2021) — or conversely “do not make sense” — or testing whether slight variations to the operationalizations that should not matter,…”
BackgroundMethodInfluentialHi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelsPreprint
Smith, E. M., & Williams, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03300 · Cited by 33
“…datasets for their directional estimate of relative levels of bias, despite some limitations (inconsistencies, data quality issues, etc.) as noted by Blodgett et al. (2021). capacity versions of BlenderBot (including those distilled from BlenderBot3B), and bias is likewise suppressed for all…”
Bridging Fairness and Environmental Sustainability in Natural Language Processing
Hessenthaler, M., Strubell, E., Hovy, D., & Lauscher, A. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.533 · Cited by 16
Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning
Luo, H., & Glass, J. R. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.89 · Cited by 15
Exploring Social Biases of Large Language Models in a College Artificial Intelligence Course
Kolisko, S., & Anderson, C. J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i13.26879 · Cited by 12
“This was done in tandem with an in-class discussion of Blodgett et al. (2021), which surveys existing bias probe tasks and highlights a number of common issues in their construction.”
Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Levy, S., John, N. A., Liu, L., Vyas, Y., Ma, J., Fujinuma, Y., Ballesteros, M., Castelli, V., & Roth, D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.634 · Cited by 18
“Fifty Shades of Bias”: Normative Ratings of Gender Bias in GPT Generated English Text
Hada, R., Seth, A., Diddee, H., & Bali, K. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.115 · Cited by 12
The Machine Speaks: Conversational AI and the Importance of Effort to Relationships of Meaning
Hartford, A., & Stein, D. J. (2024) · JMIR Mental Health · doi:10.2196/53203 · Cited by 11
Social norm bias: residual harms of fairness-aware algorithms
Cheng, M., De‐Arteaga, M., Mackey, L. W., & Kalai, A. T. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00910-8 · Cited by 15
“These works have varying definitions of stereotypes [11].”
BackgroundThe tail wagging the dog: Dataset construction biases of social bias benchmarks
Selvam, N., Dev, S., Khashabi, D., Khot, T., & Chang, K.-W. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/2023.acl-short.118 · Cited by 11
FairDistillation: Mitigating Stereotyping in Language Models
Delobelle, P., & Berendt, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26390-3_37 · Cited by 14
This prompt is measuring <mask>: evaluating bias evaluation in language models
Goldfarb-Tarrant, S., Ungless, E. L., Balkır, E., & Blodgett, S. L. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.139 · Cited by 26
Self-citationAlgorithmic bias: sexualized violence against women in GPT-3 models
Wyer, S., & Black, S. (2025) · AI and Ethics · doi:10.1007/s43681-024-00641-0 · Cited by 14
“…considers bias in relation to men, women, and people, upon evaluating popular benchmarks, the conclu - sion of this evaluation highlighted that those commonly used are limited in identifying and enabling effective mea - surement of bias and the propagation of stereotypes [10 , 17, 50 , 61].”
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI
Rosenblatt, L., Piedras, L., & Wilkins, J. (2022) · Workshop on NLP for Positive Impact (NLP4PI) · doi:10.18653/v1/2022.nlp4pi-1.2 · Cited by 11
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models
Ovalle, A., Pavasovic, K. L., Martin, L., Zettlemoyer, L., Smith, E. M., Chang, K.-W., Williams, A., & Sagun, L. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732196 · Cited by 12
“Our proposed framework for analyzing implicit reward signals suggests aligned LLMs can systematically preserve harmful gender-diverse biases from their reference models.”
AI Alignment at Your Discretion
Buyl, M., Khalaf, H., Verdun, C. M., Paes, L. M., Machado, C. C. V., & Calmon, F. P. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732194 · Cited by 18
“In this work, we define alignment discretion as the margin afforded to annotators to decide which AI behavior is “better” with respect to the alignment goals and principles .”
Havens, L., Alex, B., Bach, B., & Terras, M. (2022) · Workshop on Gender Bias in Natural Language Processing (GeBNLP) · doi:10.18653/v1/2022.gebnlp-1.4 · Cited by 9
“, 2018), many have limited efficacy, failing to address the complexity of biased language (Stańczak and Augenstein, 2021; Blodgett et al., 2021; Gonen and Goldberg, 2019).”
BackgroundBipol: A novel multi-axes bias evaluation metric with explainability for NLP
Alkhaled, L., Adewumi, T., & Sabry, S. S. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100030 · Cited by 8
SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models
Nagireddy, M., Chiazor, L., Singh, M., & Baldini, I. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i19.30142 · Cited by 8
Deciphering Stereotypes in Pre-Trained Language Models
Ma, W., Scheible, H., Wang, B., Veeramachaneni, G., Chowdhary, P., Sun, A., Koulogeorge, A., Wang, L., Yang, D., & Vosoughi, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.697 · Cited by 8
“We pursued this approach because existing stereotype examination datasets often oversimplify the task and have known quality concerns, as indicated by Blodgett et al. (2021).”
BackgroundC3AI: Crafting and Evaluating Constitutions for Constitutional AI
Kyrychenko, Y., Zhou, K., Bogucka, E., & Quercia, D. (2025) · The Web Conference · doi:10.1145/3696410.3714705 · Cited by 22
“Evaluating LLMs’ growing abilities is a challenging research area [5, 10, 12, 30].”
Building Stereotype Repositories with Complementary Approaches for Scale and Depth
Dev, S., Jha, A., Goyal, J., Tewari, D., Dave, S., & Prabhakaran, V. (2023) · Workshop on Cross-Cultural Considerations in NLP (C3NLP) · doi:10.18653/v1/2023.c3nlp-1.9 · Cited by 8
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness
Mireshghallah, F., & Berg-Kirkpatrick, T. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.152 · Cited by 15
Fine-Tuning Language Models to Mitigate Gender Bias in Sentence Encoders
Dolci, T. (2022) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice55688.2022.00036 · Cited by 7
“In fact, not considering the small amount of sentences employed, both StereoSet and CrowsPairs have been criticized for their lack of quality and a number of pitfalls [10].”
BackgroundResponsible AI measures dataset for ethics evaluation of AI systems
Rismani, S., Davis, L., Mingole, B., Rostamzadeh, N., Shelby, R. M., & Moon, A. (2025) · Scientific Data · doi:10.1038/s41597-025-06021-5 · Cited by 12
“The demand for more comprehensive synthesis is further underscored by mounting criticism from computing 14,15 , human-computer interaction (HCI) 16 , and computational social science communities 17 regarding the limitations of current measurement practices for responsible AI development.”
Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models
Görge, R., Mock, M., & Allende‐Cid, H. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732181 · Cited by 10
“StereoSet and CrowS-Pairs in particular are widely used, but also inherit significant weaknesses regarding the construction of stereotypes [6], which is why [33] presents an improved version of CrowS-Pairs.”
InfluentialResponsible AI Considerations in Text Summarization Research: A Review of Current Practices
Liu, Y. H., Cao, M., Blodgett, S. L., Cheung, J. C. K., Olteanu, A., & Trischler, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.413 · Cited by 7
Self-citationReinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection
Pujari, R., Oveson, E., Kulkarni, P., & Nouri, E. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.462 · Cited by 9
An Empirical Study on the Fairness of Pre-trained Word Embeddings
Sesari, E., Hort, M., & Sarro, F. (2022) · Workshop on Gender Bias in Natural Language Processing (GeBNLP) · doi:10.18653/v1/2022.gebnlp-1.15 · Cited by 7
“In the future, we need a deeper analysis and explanation of the numerous fairness tendencies discovered in this study, such as the correlation with explicit gender gaps and survey data (Friedman et al., 2019a,b), and the extent to which the embeddings reproduce bias (Blodgett et al., 2021).”
BackgroundLanguage model acceptability judgements are not always robust to context
Sinha, K., Gauthier, J., Mueller, A., Misra, K., Fuentes, K., Lévy, R., & Williams, A. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.333 · Cited by 12
Learning to Generate Equitable Text in Dialogue from Biased Training Data
Sicilia, A., & Alikhani, M. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.163 · Cited by 6
Ethics consideration sections in natural language processing papers
Benotti, L., & Blackburn, P. R. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.299 · Cited by 6
“Here is an example of an ECS in the Ethics in NLP track (Blodgett et al., 2021) reflecting on potential harms when it is hard to see them.”
BackgroundInvestigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques
Reusens, M., Borchert, P., Mieskes, M., Weerdt, J. D., & Baesens, B. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.175 · Cited by 12
Understanding the Effect of Model Compression on Social Bias in Large Language Models
Gonçalves, G., & Strubell, E. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.161 · Cited by 16
“This has also been noted by Blodgett et al. (2021), showing that CrowS is slightly more robust than SS by taking "extra steps to control for varying base rates be-tween groups."”
BackgroundMethodInfluentialStereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models
Jeoung, S., Ge, Y., & Diesner, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.752 · Cited by 12
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance
Subramonian, A., Yuan, X., Daumé, H., & Blodgett, S. L. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.202 · Cited by 23
Self-citationRobust Evaluation Measures for Evaluating Social Biases in Masked Language Models
Liu, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29834 · Cited by 7
Speciesism in natural language processing research
Takeshita, M., & Rzepka, R. (2024) · AI and Ethics · doi:10.1007/s43681-024-00606-3 · Cited by 7
“The exchange student became the star of all of our art shows and drama performances.”
Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages
Goldfarb-Tarrant, S., Lopez, A., Blanco, R., & Marcheggiani, D. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.272 · Cited by 7
What do Bias Measures MeasurePreprint
Dev, S., Sheng, E., Zhao, J., Sun, J., Hou, Y., Sanseverino, M., Kim, J., Peng, N., & Chang, K.-W. (2021) · arXiv (Cornell University) · Cited by 6
Metadata
- Authors
- Blodgett, S. L., Lopez, G., Olteanu, A., Sim, R., & Wallach, H.
- Affiliations
- Microsoft (United States) (US)
- 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
- 1004-1015
- OpenAlex
- W3172415559
- Cited by
- 147
- References
- 29
- Citations by year
- 2026: 13 · 2025: 17 · 2024: 21 · 2023: 55 · 2022: 34 · 2021: 7
- FWCI
- 26.22
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- stereotyping, Norwegian language, bias in language models, dataset evaluation, fairness metrics
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
