---
title: "An Empirical Study of Metrics to Measure Representational"
description: "They first define representational harm as a model systematically linking marginalized groups with… 41 references, cited by 16 papers here."
authors: ["Saghar Hosseini", "Hamid Palangi", "Ahmed Hassan Awadallah"]
year: 2023
venue: "arXiv:2301.09211"
source: "https://arxiv.org/abs/2301.09211"
doi: "10.48550/arxiv.2301.09211"
arxiv: "2301.09211"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/hosseini-2023-empirical-study-metrics-measure-representational/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hosseini-2023-empirical-study-metrics-measure-representational/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/10/) / An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models

# An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models

**Authors:** Saghar Hosseini, [Hamid Palangi](https://md.research.elamur.ai/free/en/authors/hamid-palangi/) and [Ahmed Hassan Awadallah](https://md.research.elamur.ai/free/en/authors/ahmed-hassan-awadallah/) · **Year:** 2023 · **Venue:** arXiv:2301.09211 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2301.09211) · [PDF](https://arxiv.org/pdf/2301.09211) · [DOI 10.48550/arxiv.2301.09211](https://doi.org/10.48550/arxiv.2301.09211) · [arXiv 2301.09211](https://arxiv.org/abs/2301.09211) · [OpenAlex](https://openalex.org/W4385734253)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [16](https://md.research.elamur.ai/free/en/papers/hosseini-2023-empirical-study-metrics-measure-representational/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Pre-trained language models absorb societal biases from human-written training text. Much of this harm is implicit, such as microaggressions and stereotypes, and toxicity detectors tend to miss it. Existing bias metrics are also often poorly conceptualized. The authors follow a measurement-modeling approach. They first define representational harm as a model systematically linking marginalized groups with negative perceptions. They then operationalize it by comparing how likely a model finds implicitly harmful statements versus benign ones about each group. The comparison uses a human-annotated subset of ToxiGen covering 13 demographics.

With this likelihood-based metric, they audit 24 popular PTLMs, including BERT, RoBERTa, ELECTRA, ALBERT, GPT-2 and XLNet variants. They compare the scores with other bias measures and study how network shape relates to harm. The new metric agrees with most gender-focused metrics from earlier work. Favoring deeper rather than wider networks lowered harm for some model families. The metric works with any dataset that labels examples as harmful or benign, and the code is released.

## Key points
- **Data:** about 10,000 GPT-3-generated ToxiGen sentences, each rated by 3 crowd workers on a 1–5 toxicity scale. Only about 4% are lewd, so the harm is mostly subtle rather than overt.
- **Models:** 24 PTLMs, from DistilBERT and mobileBERT up to GPT-2-xl and ALBERT-xxlarge-v2.
- **Average safety scores across models:** ALBERT-large-v2 scored highest (0.392) and BERT-large-cased lowest (0.264).
- **ImplicitHate safety scores:** GPT-2 and XLNet models scored lowest (about 0.25–0.27), while DistilRoBERTa scored highest (about 0.39).
- **Depth vs. width experiment:** GPT-2 students were distilled from GPT-2 for 1 epoch on OpenWebText, with 2–12 layers and hidden sizes of 128–768. Each was then few-shot tuned on 500 examples per benchmark (WikiText2, WikiText103, LAMBDA, PTB).
- **Resources:** code and data are available at github.com/microsoft/SafeNLP.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 325 works · 142,931 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 543 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works

## Cite

Cite as: Saghar Hosseini, Hamid Palangi and Ahmed Hassan Awadallah. 2023. An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models. arXiv:2301.09211.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{hosseini2023empirical,
  title = {{An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models}},
  author = {Saghar Hosseini, Hamid Palangi and Ahmed Hassan Awadallah},
  year = {2023},
  doi = {10.48550/arxiv.2301.09211},
  eprint = {2301.09211},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2301.09211}
}
```

- [← previous ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers](https://md.research.elamur.ai/free/en/papers/zhang-2023-algo-synthesizing-algorithmic-programs-llm/)
- [next → Connective Prediction for Implicit Discourse Relation Recognition via Knowledge Distillation](https://md.research.elamur.ai/free/en/papers/wu-2023-connective-prediction-implicit-discourse-relation/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/10/)

## References

41 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Su Lin Blodgett, Gilsinia Lopez, Alexandra Olteanu, Robert Sim, and Hanna Wallach. Stereotyping Norwegian salmon: An inventory of pitfalls in fairness benchmark datasets. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confe… [find](https://scholar.google.com/scholar?q=Su+Lin+Blodgett%2C+Gilsinia+Lopez%2C+Alexandra+Olteanu%2C+Robert+Sim%2C+and+Hanna+Wallach%2E+Stereotyping+Norwegian+salmon%3A+An+inventory+of+pitfalls+in+fairness+benchmark+datasets%2E+In+Proceedings+of+the+59th+An)
2. Luke Breitfeller, Emily Ahn, David Jurgens, and Yulia Tsvetkov. [Finding microaggressions in the wild: A case for locating elusive phenomena in social media posts](https://md.research.elamur.ai/free/en/papers/breitfeller-2019-finding-microaggressions-wild-case-locating/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on N…
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D 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 Ziegler, Jeffrey Wu, Clemens Winter, Chri… [find](https://scholar.google.com/scholar?q=Tom+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+D+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+Sandhini+Agarwal%2C+Ariel+Herbert%2DVoss%2C+Gretchen)
4. Curran Associates, Inc., 2020. URL [https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf](https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf). [↗](https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf)
5. Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183–186, 2017. doi: 10.1126/ science.aal4230. URL [https://www.science.org/doi/abs/10.1126/science](https://www.science.org/doi/abs/10.1126/science). aal4230. [↗](https://www.science.org/doi/abs/10.1126/science)
6. Yang Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, and Aram Galstyan. [On the intrinsic and extrinsic fairness evaluation metrics for contextualized language representations](https://md.research.elamur.ai/free/en/papers/cao-2022-intrinsic-extrinsic-fairness-evaluation-metrics/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics…
7. Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. Electra: Pre-training text encoders as discriminators rather than generators. arXiv, 2020. doi: 10.48550/ARXIV.2003.10555. URL https://arxiv.org/abs/2003.10555. [↗](https://arxiv.org/abs/2003.10555)
8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volum…
9. Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, and Rahul Gupta. Bold: Dataset and metrics for measuring biases in open-ended language generation. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21, pp. 862–… — [doi:10.1145/3442188.3445924](https://doi.org/10.1145/3442188.3445924) [find](https://scholar.google.com/scholar?q=Jwala+Dhamala%2C+Tony+Sun%2C+Varun+Kumar%2C+Satyapriya+Krishna%2C+Yada+Pruksachatkun%2C+Kai%2DWei+Chang%2C+and+Rahul+Gupta%2E+Bold%3A+Dataset+and+metrics+for+measuring+biases+in+open%2Dended+language+generation%2E+In+Proce)
10. Mai ElSherief, Caleb Ziems, David Muchlinski, Vaishnavi Anupindi, Jordyn Seybolt, Munmun De Choudhury, and Diyi Yang. [Latent hatred: A benchmark for understanding implicit hate speech](https://md.research.elamur.ai/free/en/papers/elsherief-2021-latent-hatred-benchmark-understanding-implicit/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 345–363, Online and…
11. Aaron Gokaslan, Vanya Cohen, Ellie Pavlick, and Stefanie Tellex. Openwebtext corpus, 2019. URL [http://Skylion007.github.io/OpenWebTextCorpus](http://Skylion007.github.io/OpenWebTextCorpus). [↗](http://Skylion007.github.io/OpenWebTextCorpus)
12. Sophie Groenwold, Lily Ou, Aesha Parekh, Samhita Honnavalli, Sharon Levy, Diba Mirza, and William Yang Wang. [Investigating African-American Vernacular English in transformer-based text generation](https://md.research.elamur.ai/free/en/papers/groenwold-2020-investigating-african-american-vernacular-english/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.…
13. Wei Guo and Aylin Caliskan. Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases, pp. 122–133. Association for Computing Machinery, New York, NY, USA, 2021. ISBN 9781450384735. URL https://doi.org/10. 1145/3461702.3462536. [find](https://scholar.google.com/scholar?q=Wei+Guo+and+Aylin+Caliskan%2E+Detecting+Emergent+Intersectional+Biases%3A+Contextualized+Word+Embeddings+Contain+a+Distribution+of+Human%2Dlike+Biases%2C+pp%2E+122%E2%80%93133%2E+Association+for+Computing+Machinery%2C+New+)
14. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. [ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
15. Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. [Distilling the knowledge in a neural network](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/). ArXiv, abs/1503.02531, 2015.
16. Svetlana Kiritchenko and Saif Mohammad. [Examining gender and race bias in two hundred sentiment analysis systems](https://md.research.elamur.ai/free/en/papers/kiritchenko-2018-examining-gender-race-bias-two/). In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pp. 43–53, New Orleans, Louisiana, June 2018. Association for Computational Linguistics. doi: 10.18…
17. Keita Kurita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. [Measuring bias in contextualized word representations](https://md.research.elamur.ai/free/en/papers/kurita-2019-measuring-bias-contextualized-word-representations/). In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pp. 166–172, Florence, Italy, August 2019. Association for Computational Linguistics. d…
18. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. [Albert: A lite bert for self-supervised learning of language representations](https://md.research.elamur.ai/free/en/papers/lan-2019-albert-lite-bert-self-supervised/). In International Conference on Learning Representations, 2020. URL [https://openreview.net/forum?](https://openreview.net/forum?) id=H1eA7AEtvS. [↗](https://openreview.net/forum?)
19. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv, 2019. doi: 10.48550/ARXIV.1907.11692. URL https://arxiv.org/abs/ 1907.11692. [↗](https://arxiv.org/abs/)
20. H. B. Mann and D. R. Whitney. On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other. The Annals of Mathematical Statistics, 18(1):50 – 60, 1947. doi: 10.1214/ aoms/1177730491. URL https://doi.org/10.1214/aoms/1177730491. — [doi:10.1214/aoms/1177730491](https://doi.org/10.1214/aoms/1177730491) [↗](https://doi.org/10.1214/aoms/1177730491)
21. Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. [Building a large annotated corpus of English: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational Linguistics, 19(2):313–330, 1993. URL [https://www.aclweb.org/anthology/J93-2004](https://www.aclweb.org/anthology/J93-2004). [↗](https://www.aclweb.org/anthology/J93-2004)
22. Chandler May, Alex Wang, Shikha Bordia, Samuel R. Bowman, and Rachel Rudinger. [On measuring social biases in sentence encoders](https://md.research.elamur.ai/free/en/papers/may-2019-measuring-social-biases-sentence-encoders/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short…
23. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. [Pointer sentinel mixture models](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/). arXiv, 2016.
24. Moin Nadeem, Anna Bethke, and Siva Reddy. [Stereoset: Measuring stereotypical bias in pretrained language models](https://md.research.elamur.ai/free/en/papers/nadeem-2021-stereoset-measuring-stereotypical-bias-pretrained/). ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Confe…
25. Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. [CrowS-pairs: A challenge dataset for measuring social biases in masked language models](https://md.research.elamur.ai/free/en/papers/nangia-2020-crows-pairs-challenge-dataset-measuring/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1953–1967, Online, November 2020. Associat…
26. Denis Paperno, Germán Kruszewski, Angeliki Lazaridou, Ngoc Quan Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernández. [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://md.research.elamur.ai/free/en/papers/paperno-2016-lambada-dataset-word-prediction-requiring/). In Proceedings of the 54th Annual Meeting of the Association for Comp…
27. Rebecca Qian, Candace Ross, Jude Fernandes, Eric Smith, Douwe Kiela, and Adina Williams. Perturbation augmentation for fairer nlp, 2022. URL [https://dynabench.org/fairer_](https://dynabench.org/fairer_) nlp.pdf. [↗](https://dynabench.org/fairer_)
28. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners, 2019. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeff+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+Language+models+are+unsupervised+multitask+learners%2C+2019%2E)
29. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. [Gender bias in coreference resolution](https://md.research.elamur.ai/free/en/papers/rudinger-2018-gender-bias-coreference-resolution/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 8–14, New O…
30. Julian Salazar, Davis Liang, Toan Q. Nguyen, and Katrin Kirchhoff. [Masked language model scoring](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2699–2712, Online, July 2020. Association for Computational Linguistics. doi: 10.18653/v1/2020. acl-main.2…
31. Patrick Schramowski, Cigdem Turan, Nico Andersen, Constantin A. Rothkopf, and Kristian Kersting. Large pre-trained language models contain human-like biases of what is right and wrong to do. Nature Machine Intelligence, 2022. [find](https://scholar.google.com/scholar?q=Patrick+Schramowski%2C+Cigdem+Turan%2C+Nico+Andersen%2C+Constantin+A%2E+Rothkopf%2C+and+Kristian+Kersting%2E+Large+pre%2Dtrained+language+models+contain+human%2Dlike+biases+of+what+is+right+and+wrong+to+do%2E+Nature+Ma)
32. Viviane Seyranian, Hazel Atuel, and William D. Crano. Dimensions of majority and minority groups. Group Processes & Intergroup Relations, 11(1):21–37, 2008. doi: 10.1177/1368430207084843. URL https://doi.org/10.1177/1368430207084843. — [doi:10.1177/1368430207084843](https://doi.org/10.1177/1368430207084843) [↗](https://doi.org/10.1177/1368430207084843)
33. Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, and Nanyun Peng. [The woman worked as a babysitter: On biases in language generation](https://md.research.elamur.ai/free/en/papers/sheng-2019-woman-worked-as-babysitter-biases/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (E…
34. Emily Sheng, Kai Wei Chang, Premkumar Natarajan, and Nanyun Peng. [Societal biases in language generation: Progress and challenges](https://md.research.elamur.ai/free/en/papers/sheng-2021-societal-biases-language-generation-progress/). ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Procee…
35. Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan, and Y-Lan Boureau. Controlling style in generated dialogue. arXiv, 2020. doi: 10.48550/ARXIV.2009.10855. URL https://arxiv.org/abs/2009.10855. — [doi:10.48550/arxiv.2009.10855](https://doi.org/10.48550/arxiv.2009.10855) [↗](https://arxiv.org/abs/2009.10855)
36. Eric Michael Smith, Melissa Hall, Melanie Kambadur, Eleonora Presani, and Adina Williams. "i’m sorry to hear that": finding bias in language models with a holistic descriptor dataset. arXiv, 2022. doi: 10.48550/ARXIV.2205.09209. URL https://arxiv.org/abs/2205.09209. — [doi:10.48550/arxiv.2205.09209](https://doi.org/10.48550/arxiv.2205.09209) [↗](https://arxiv.org/abs/2205.09209)
37. Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. [Well-read students learn better: On the importance of pre-training compact models](https://md.research.elamur.ai/free/en/papers/turc-2019-well-read-students-learn-better/). arXiv, 2019. doi: 10.48550/ARXIV.1908.08962. URL https://arxiv.org/abs/1908.08962. [↗](https://arxiv.org/abs/1908.08962)
38. Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. Investigating gender bias in language models using causal mediation analysis. NeurIPS, 2020. URL [https://github.com/sebastianGehrmann/](https://github.com/sebastianGehrmann/) CausalMediationAnalysis. [↗](https://github.com/sebastianGehrmann/)
39. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. [GLUE: A multi-task benchmark and analysis platform for natural language understanding](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/). In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353–355, Brussel…
40. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. [Gender bias in coreference resolution: Evaluation and debiasing methods](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volum…
41. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, and Kai-Wei Chang. [Gender bias in contextualized word embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long…

*Updated 31 October 2026*