CoChat
Sign Up
Cited by 14Ethics and Social Impacts of AIHate Speech and Cyberbullying DetectionExplainable Artificial Intelligence (XAI)

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

On the Independence of Association Bias and Empirical Fairness in Language Models

Open access
Cabello, Laura, Jørgensen, Anna Katrine, Søgaard, Anders·2023·2023 ACM Conference on Fairness, Accountability, and Transparency
DOI 10.1145/3593013.3594004
Open this paper in CoChat — free accountOpen PDF

Abstract

The societal impact of pre-trained language models has prompted researchers to probe them for strong associations between protected attributes and value-loaded terms, from slur to prestigious job titles. Such work is said to probe models for bias or fairness—or such probes ‘into representational biases’ are said to be ‘motivated by fairness’—suggesting an intimate connection between bias and fairness. We provide conceptual clarity by distinguishing between association biases [11] and empirical fairness [56] and show the two can be independent. Our main contribution, however, is showing why this should not come as a surprise. To this end, we first provide a thought experiment, showing how association bias and empirical fairness can be completely orthogonal. Next, we provide empirical evidence that there is no correlation between bias metrics and fairness metrics across the most widely used language models. Finally, we survey the sociological and psychological literature and show how this literature provides ample support for expecting these metrics to be uncorrelated.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3593013.3594004

Cites

9 of 9 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Word associations with protected attributes may be a poor proxy for downstream disparities, which may limit distribution-based metrics that rely on vectors of co-occurrence counts.

    “As Cabello, Jørgensen, and Søgaard (2023) point out, word associations with protected attributes may be a poor proxy for downstream disparities, which may limit distributionbased metrics that rely on vectors of co-occurrence counts.”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Cabello, Jørgensen, and Søgaard 2023

    Section 4 and the Bias section report that word-association bias is often independent of empirical fairness, supporting the warning that associations can be a poor proxy for downstream disparities. The paper discusses association metrics based on embeddings and model probabilities, but the passages do not establish the specific limitation claimed for distribution-based metrics using vectors of co-occurrence counts. Page numbers are unavailable in our copy. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • Biases in the embedding space have only weak or inconsistent relationships with biases in downstream tasks.

    “Several works point out that biases in the embedding space have only weak or inconsistent relationships with biases in downstream tasks (Cabello, Jørgensen, and Søgaard 2023; Cao et al. 2022a; Goldfarb-Tarrant et al. 2021; Orgad and Belinkov 2022; Orgad, Goldfarb-Tarrant, and Belinkov 2022; Steed et al. 2022).”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Cabello, Jørgensen, and Søgaard 2023

  • Associations between representations of protected attributes and other words can be independent of downstream performance disparities, if certain assumptions of social groups' language use are violated.

    “Cabello, Jørgensen, and Søgaard (2023) illustrate that associations between the representations of protected attribute and other words can be independent of downstream performance disparities, if certain assumptions of social groups' language use are violated.”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Cabello, Jørgensen, and Søgaard 2023

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

Flagged first, then by citations

Research works printed but not linked: 61

  1. Ameen Ali , Thomas Schnake , Oliver Eberle , Grégoire Montavon , Klaus-Robert Müller , and Lior Wolf . 2022 . XAI for Transformers: Better Explanations through Conservative Propagation . In International Conference on Machine Learning, ICML 2022 , 17-23 July 2022, Baltimore, Maryland, USA(Proceedings of Machine Learning Research , Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (Eds.). PMLR, 435– 451 . https://proceedings.mlr.press/v162/ali22a.html Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, and Lior Wolf. 2022. XAI for Transformers: Better Explanations through Conservative Propagation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA(Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (Eds.). PMLR, 435–451. https://proceedings.mlr.press/v162/ali22a.html
  2. Ameen Ali Thomas Schnake Oliver Eberle Grégoire Montavon Klaus-Robert Müller and Lior Wolf. 2022. XAI for Transformers: Better Explanations through Conservative Propagation. https://doi.org/10.48550/ARXIV.2202.07304 10.48550/ARXIV.2202.07304 · DOI
  3. Ameen Ali Thomas Schnake Oliver Eberle Grégoire Montavon Klaus-Robert Müller and Lior Wolf. 2022. XAI for Transformers: Better Explanations through Conservative Propagation. https://doi.org/10.48550/ARXIV.2202.07304 · DOI
  4. Lizzie Barmes . 2009 . Equality Law and Experimentation: The Positive Action Challenge . The Cambridge Law Journal 68 , 3 (2009), 623 – 654 . http://www.jstor.org/stable/40388838 Lizzie Barmes. 2009. Equality Law and Experimentation: The Positive Action Challenge. The Cambridge Law Journal 68, 3 (2009), 623–654. http://www.jstor.org/stable/40388838 · DOI
  5. Marion Bartl , Malvina Nissim , and Albert Gatt . 2020 . Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias . In Proceedings of the Second Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics, Barcelona, Spain (Online), 1–16 . https://aclanthology.org/2020.gebnlp-1.1 Marion Bartl, Malvina Nissim, and Albert Gatt. 2020. Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias. In Proceedings of the Second Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics, Barcelona, Spain (Online), 1–16. https://aclanthology.org/2020.gebnlp-1.1
  6. Sudeep Bhatia . 2017 . The semantic representation of prejudice and stereotypes . Cognition 164 (2017), 46 – 60 . https://doi.org/10.1016/j.cognition.2017.03.016 10.1016/j.cognition.2017.03.016 Sudeep Bhatia. 2017. The semantic representation of prejudice and stereotypes. Cognition 164 (2017), 46–60. https://doi.org/10.1016/j.cognition.2017.03.016 · DOI
  7. Felix Biessmann. 2016. Automating political bias prediction. arXiv preprint. arXiv:1608.02195. Felix Biessmann. 2016. Automating political bias prediction. arXiv preprint. arXiv:1608.02195. · arXiv
  8. Tolga Bolukbasi , Kai-Wei Chang , James Y Zou , Venkatesh Saligrama , and Adam T Kalai . 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings . In Advances in Neural Information Processing Systems , D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.). Vol. 29 . Curran Associates, Inc. https://proceedings.neurips.cc/paper/ 2016 /file/a486cd07e4ac3d270571622f4f316ec5-Paper.pdf Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.). Vol. 29. Curran Associates, Inc.https://proceedings.neurips.cc/paper/2016/file/a486cd07e4ac3d270571622f4f316ec5-Paper.pdf
  9. Marc-Etienne Brunet , Colleen Alkalay-Houlihan , Ashton Anderson , and Richard Zemel . 2019 . Understanding the Origins of Bias in Word Embeddings . In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research , Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 803– 811 . https://proceedings.mlr.press/v97/brunet19a.html Marc-Etienne Brunet, Colleen Alkalay-Houlihan, Ashton Anderson, and Richard Zemel. 2019. Understanding the Origins of Bias in Word Embeddings. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 803–811. https://proceedings.mlr.press/v97/brunet19a.html
  10. Aylin Caliskan , Pimparkar Parth Ajay , Tessa Charlesworth , Robert Wolfe , and Mahzarin R. Banaji . 2022. Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics . In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society ( Oxford, United Kingdom) (AIES ’22). Association for Computing Machinery, New York, NY, USA, 156–170. https://doi.org/10.1145/3514094.3534162 10.1145/3514094.3534162 Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, and Mahzarin R. Banaji. 2022. Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (Oxford, United Kingdom) (AIES ’22). Association for Computing Machinery, New York, NY, USA, 156–170. https://doi.org/10.1145/3514094.3534162 · DOI
  11. Aylin Caliskan , Joanna J. Bryson , and Arvind Narayanan . 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334 ( 2017 ), 183–186. https://doi.org/10.1126/science.aal4230 arXiv:https://www.science.org/doi/pdf/10.1126/science.aal4230 10.1126/science.aal4230 Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334 (2017), 183–186. https://doi.org/10.1126/science.aal4230 arXiv:https://www.science.org/doi/pdf/10.1126/science.aal4230 · DOI · Paper page
  12. Yang Cao , Yada Pruksachatkun , Kai-Wei Chang , Rahul Gupta , Varun Kumar , Jwala Dhamala , and Aram Galstyan . 2022 . On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations . In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics , Dublin, Ireland, 561–570. https://doi.org/10. 18653/v1/2022.acl-short.62 10.18653/v1 Yang Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, and Aram Galstyan. 2022. On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Dublin, Ireland, 561–570. https://doi.org/10.18653/v1/2022.acl-short.62 · DOI
  13. Alessandro Castelnovo , Riccardo Crupi , Greta Greco , Daniele Regoli , Ilaria Giuseppina Penco , and Andrea Claudio Cosentini . 2022 . A clarification of the nuances in the fairness metrics landscape . Scientific Reports 12 , 1 (March 2022). https://doi.org/10.1038/s41598-022-07939-1 10.1038/s41598-022-07939-1 Alessandro Castelnovo, Riccardo Crupi, Greta Greco, Daniele Regoli, Ilaria Giuseppina Penco, and Andrea Claudio Cosentini. 2022. A clarification of the nuances in the fairness metrics landscape. Scientific Reports 12, 1 (March 2022). https://doi.org/10.1038/s41598-022-07939-1 · DOI
  14. Ilias Chalkidis , Tommaso Pasini , Sheng Zhang , Letizia Tomada , Sebastian Schwemer , and Anders Søgaard . 2022 . FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing . In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics , Dublin, Ireland, 4389–4406. https://doi.org/10. 18653/v1/2022.acl-long.301 10.18653/v1 Ilias Chalkidis, Tommaso Pasini, Sheng Zhang, Letizia Tomada, Sebastian Schwemer, and Anders Søgaard. 2022. FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 4389–4406. https://doi.org/10.18653/v1/2022.acl-long.301 · DOI
  15. Kaytlin Chaloner and Alfredo Maldonado . 2019 . Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories . In Proceedings of the First Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics , Florence, Italy, 25–32. https://doi.org/10. 18653/v1/W 19 - 3804 10.18653/v1 Kaytlin Chaloner and Alfredo Maldonado. 2019. Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics, Florence, Italy, 25–32. https://doi.org/10.18653/v1/W19-3804 · DOI
  16. Kai-Wei Chang , Vinodkumar Prabhakaran , and Vicente Ordonez . 2019. Bias and Fairness in Natural Language Processing . In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts . Association for Computational Linguistics , Hong Kong , China. https://aclanthology.org/D19- 2004 Kai-Wei Chang, Vinodkumar Prabhakaran, and Vicente Ordonez. 2019. Bias and Fairness in Natural Language Processing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts. Association for Computational Linguistics, Hong Kong, China. https://aclanthology.org/D19-2004
  17. Wei-Fan Chen , Khalid Al Khatib , Henning Wachsmuth , and Benno Stein . 2020 . Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity . In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science. Association for Computational Linguistics, Online, 149–154 . https://doi.org/10.18653/v1/2020.nlpcss-1.16 10.18653/v1 Wei-Fan Chen, Khalid Al Khatib, Henning Wachsmuth, and Benno Stein. 2020. Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity. In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science. Association for Computational Linguistics, Online, 149–154. https://doi.org/10.18653/v1/2020.nlpcss-1.16 · DOI
  18. Kate Crawford . 2017 . The trouble with bias . In Conference on Neural Information Processing Systems, invited speaker. Kate Crawford. 2017. The trouble with bias. In Conference on Neural Information Processing Systems, invited speaker.
  19. Erenay Dayanik and Sebastian Padó . 2020 . Masking Actor Information Leads to Fairer Political Claims Detection . In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 4385–4391 . https://doi.org/10.18653/v1/2020.acl-main.404 10.18653/v1 Erenay Dayanik and Sebastian Padó. 2020. Masking Actor Information Leads to Fairer Political Claims Detection. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 4385–4391. https://doi.org/10.18653/v1/2020.acl-main.404 · DOI
  20. Pieter Delobelle , Ewoenam Kwaku Tokpo , Toon Calders, and Bettina Berendt. 2021 . Measuring Fairness with Biased Rulers : A Survey on Quantifying Biases in Pretrained Language Models. CoRR abs/2112.07447 (2021). https://arxiv.org/abs/2112.07447 Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, and Bettina Berendt. 2021. Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models. CoRR abs/2112.07447 (2021). https://arxiv.org/abs/2112.07447 · arXiv
  21. Coen Van Duijnhoven . 2018. Predicting political preference through content- and stylistic text features and distant labeling. Master’s thesis . Tilburg University . Coen Van Duijnhoven. 2018. Predicting political preference through content- and stylistic text features and distant labeling. Master’s thesis. Tilburg University.
  22. Sorelle A. Friedler Carlos Scheidegger and Suresh Venkatasubramanian. 2016. On the (im)possibility of fairness. https://doi.org/10.48550/ARXIV.1609.07236 · DOI · Paper page
  23. Niklas Friedrich , Anne Lauscher , Simone Paolo Ponzetto , and Goran Glavaš . 2021 . DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces . In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, Online, 91–98 . https://doi.org/10.18653/v1/2021.eacl-demos.11 10.18653/v1 Niklas Friedrich, Anne Lauscher, Simone Paolo Ponzetto, and Goran Glavaš. 2021. DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, Online, 91–98. https://doi.org/10.18653/v1/2021.eacl-demos.11 · DOI
  24. Seraphina Goldfarb-Tarrant , Rebecca Marchant , Ricardo Muñoz Sánchez , Mugdha Pandya, and Adam Lopez. 2021 . Intrinsic Bias Metrics Do Not Correlate with Application Bias. In 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). Association for Computational Linguistics, Online, 1926–1940. https://doi.org/10.18653/v1/2021.acl-long.150 10.18653/v1 Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sánchez, Mugdha Pandya, and Adam Lopez. 2021. Intrinsic Bias Metrics Do Not Correlate with Application Bias. In 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). Association for Computational Linguistics, Online, 1926–1940. https://doi.org/10.18653/v1/2021.acl-long.150 · DOI · Paper page
  25. Hila Gonen and Yoav Goldberg . 2019 . Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them . 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 Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 609–614. https://doi.org/10. 18653/v1/N 19 - 1061 10.18653/v1 Hila Gonen and Yoav Goldberg. 2019. Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them. 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 Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 609–614. https://doi.org/10.18653/v1/N19-1061 · DOI
  26. Victor Petrén Bach Hansen and Anders Søgaard . 2021. Is the Lottery Fair? Evaluating Winning Tickets Across Demographics . In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 . Association for Computational Linguistics , Online , 3214–3224. https://doi.org/10.18653/v1/2021.findings-acl.284 10.18653/v1 Victor Petrén Bach Hansen and Anders Søgaard. 2021. Is the Lottery Fair? Evaluating Winning Tickets Across Demographics. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online, 3214–3224. https://doi.org/10.18653/v1/2021.findings-acl.284 · DOI
  27. Tatsunori B. Hashimoto , Megha Srivastava , Hongseok Namkoong , and Percy Liang . 2018 . Fairness Without Demographics in Repeated Loss Minimization . In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan , Stockholm, Sweden , July 10-15, 2018(Proceedings of Machine Learning Research, Vol. 80), Jennifer G. Dy and Andreas Krause (Eds.). PMLR, 1934–1943. http://proceedings.mlr.press/v80/hashimoto18a.html Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, and Percy Liang. 2018. Fairness Without Demographics in Repeated Loss Minimization. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018(Proceedings of Machine Learning Research, Vol. 80), Jennifer G. Dy and Andreas Krause (Eds.). PMLR, 1934–1943. http://proceedings.mlr.press/v80/hashimoto18a.html
  28. Brian Hedden . 2021 . On Statistical Criteria of Algorithmic Fairness . Philosophy and Public Affairs 49 , 2 (2021), 209 – 231 . https://doi.org/10.1111/papa.12189 10.1111/papa.12189 Brian Hedden. 2021. On Statistical Criteria of Algorithmic Fairness. Philosophy and Public Affairs 49, 2 (2021), 209–231. https://doi.org/10.1111/papa.12189 · DOI
  29. P.J. Henry , Sarah E. Butler , and Mark J. Brandt . 2014 . The influence of target group status on the perception of the offensiveness of group-based slurs . Journal of Experimental Social Psychology 53 (2014), 185 – 192 . https://doi.org/10.1016/j.jesp.2014.03.012 10.1016/j.jesp.2014.03.012 P.J. Henry, Sarah E. Butler, and Mark J. Brandt. 2014. The influence of target group status on the perception of the offensiveness of group-based slurs. Journal of Experimental Social Psychology 53 (2014), 185–192. https://doi.org/10.1016/j.jesp.2014.03.012 · DOI
  30. Harry Holzer and David Neumark . 2000 . Assessing Affirmative Action . Journal of Economic Literature 38 , 3 (September 2000), 483–568. https://doi.org/10.1257/jel.38.3.483 10.1257/jel.38.3.483 Harry Holzer and David Neumark. 2000. Assessing Affirmative Action. Journal of Economic Literature 38, 3 (September 2000), 483–568. https://doi.org/10.1257/jel.38.3.483 · DOI
  31. Jacob Jensen , Ethan Kaplan , Suresh Naidu , and Laurence Wilse-Samson . 2012 . Political Polarization and the Dynamics of Political Language: Evidence from 130 Years of Partisan Speech . Brookings Papers on Economic Activity 43 , 2 (Fall) (2012), 1–81. https://ideas.repec.org/a/bin/bpeajo/v43y2012i2012-02p1-81.html Jacob Jensen, Ethan Kaplan, Suresh Naidu, and Laurence Wilse-Samson. 2012. Political Polarization and the Dynamics of Political Language: Evidence from 130 Years of Partisan Speech. Brookings Papers on Economic Activity 43, 2 (Fall) (2012), 1–81. https://ideas.repec.org/a/bin/bpeajo/v43y2012i2012-02p1-81.html
  32. Masahiro Kaneko , Danushka Bollegala , and Naoaki Okazaki . 2022 . Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks . In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 1299–1310 . https://aclanthology.org/2022.coling-1.111 Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. 2022. Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 1299–1310. https://aclanthology.org/2022.coling-1.111
  33. Jon Kleinberg Sendhil Mullainathan and Manish Raghavan. 2016. Inherent Trade-Offs in the Fair Determination of Risk Scores. https://doi.org/10.48550/ARXIV.1609.05807 · DOI · Paper page
  34. Anne Lauscher , Tobias Lueken , and Goran Glavaš . 2021 . Sustainable Modular Debiasing of Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2021 . Association for Computational Linguistics, Punta Cana, Dominican Republic, 4782–4797. https://doi.org/10. 18653/v1/2021.findings-emnlp. 411 10.18653/v1 Anne Lauscher, Tobias Lueken, and Goran Glavaš. 2021. Sustainable Modular Debiasing of Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, 4782–4797. https://doi.org/10.18653/v1/2021.findings-emnlp.411 · DOI
  35. Wen Li and Markus Dickinson . 2017 . Gender Prediction for Chinese Social Media Data . In Proceedings of Recent Advances in Natural Language Processing. Wen Li and Markus Dickinson. 2017. Gender Prediction for Chinese Social Media Data. In Proceedings of Recent Advances in Natural Language Processing.
  36. Haochen Liu , Jamell Dacon , Wenqi Fan , Hui Liu , Zitao Liu , and Jiliang Tang . 2020 . Does Gender Matter? Towards Fairness in Dialogue Systems . In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), 4403–4416 . https://doi.org/10.18653/v1/2020.coling-main.390 10.18653/v1 Haochen Liu, Jamell Dacon, Wenqi Fan, Hui Liu, Zitao Liu, and Jiliang Tang. 2020. Does Gender Matter? Towards Fairness in Dialogue Systems. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), 4403–4416. https://doi.org/10.18653/v1/2020.coling-main.390 · DOI
  37. Subha Maity Debarghya Mukherjee Mikhail Yurochkin and Yuekai Sun. 2020. Does enforcing fairness mitigate biases caused by subpopulation shift?https://doi.org/10.48550/ARXIV.2011.03173 10.48550/ARXIV.2011.03173 · DOI
  38. Subha Maity Debarghya Mukherjee Mikhail Yurochkin and Yuekai Sun. 2020. Does enforcing fairness mitigate biases caused by subpopulation shift?https://doi.org/10.48550/ARXIV.2011.03173 · DOI
  39. Ninareh Mehrabi , Fred Morstatter , Nripsuta Saxena , Kristina Lerman , and Aram Galstyan . 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6 , Article 115 (jul 2021 ), 35 pages. https://doi.org/10.1145/3457607 10.1145/3457607 Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6, Article 115 (jul 2021), 35 pages. https://doi.org/10.1145/3457607 · DOI · Paper page
  40. Thomas Miconi . 2017. The impossibility of "fairness": a generalized impossibility result for decisions. arXiv: Applications ( 2017 ). https://doi.org/10.48550/ARXIV.1707.01195 10.48550/ARXIV.1707.01195 Thomas Miconi. 2017. The impossibility of "fairness": a generalized impossibility result for decisions. arXiv: Applications (2017). https://doi.org/10.48550/ARXIV.1707.01195 · DOI
  41. Antonio Alexander Morgan-Lopez , Annice E Kim , Robert F. Chew , and Paul Ruddle . 2017. Predicting age groups of Twitter users based on language and metadata features. PLoS ONE 12 ( 2017 ). Antonio Alexander Morgan-Lopez, Annice E Kim, Robert F. Chew, and Paul Ruddle. 2017. Predicting age groups of Twitter users based on language and metadata features. PLoS ONE 12 (2017).
  42. Mike Noon . 2010 . The shackled runner: time to rethink positive discrimination?Work , Employment and Society 24 , 4 (2010), 728 – 739 . https://doi.org/10.1177/0950017010380648 arXiv:https://doi.org/10.1177/0950017010380648 10.1177/0950017010380648 Mike Noon. 2010. The shackled runner: time to rethink positive discrimination?Work, Employment and Society 24, 4 (2010), 728–739. https://doi.org/10.1177/0950017010380648 arXiv:https://doi.org/10.1177/0950017010380648 · DOI
  43. Rebecca Qian Candace Ross Jude Fernandes Eric Smith Douwe Kiela and Adina Williams. 2022. Perturbation Augmentation for Fairer NLP. https://doi.org/10.48550/ARXIV.2205.12586 10.48550/ARXIV.2205.12586 · DOI
  44. Rebecca Qian Candace Ross Jude Fernandes Eric Smith Douwe Kiela and Adina Williams. 2022. Perturbation Augmentation for Fairer NLP. https://doi.org/10.48550/ARXIV.2205.12586 · DOI
  45. John Rawls . 1971. A Theory of Justice (1 ed.) . Belknap Press of Harvard University Press , Cambridge, Massachussets . John Rawls. 1971. A Theory of Justice (1 ed.). Belknap Press of Harvard University Press, Cambridge, Massachussets.
  46. Charan Reddy , Deepak Sharma , Soroush Mehri , Adriana Romero Soriano , Samira Shabanian , and Sina Honari . 2021 . Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics . In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.). Vol. 1 . https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/file/2723d092b63885e0d7c260cc007e8b9d-Paper-round1.pdf Charan Reddy, Deepak Sharma, Soroush Mehri, Adriana Romero Soriano, Samira Shabanian, and Sina Honari. 2021. Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.). Vol. 1. https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/file/2723d092b63885e0d7c260cc007e8b9d-Paper-round1.pdf
  47. Katherine Ritchie . 2017 . Social Identity, Indexicality, and the Appropriation of Slurs . Croatian Journal of Philosophy 17 , 2 (2017), 155 – 180 . Katherine Ritchie. 2017. Social Identity, Indexicality, and the Appropriation of Slurs. Croatian Journal of Philosophy 17, 2 (2017), 155–180.
  48. Alexey Romanov Maria De-Arteaga Hanna Wallach Jennifer Chayes Christian Borgs Alexandra Chouldechova Sahin Geyik Krishnaram Kenthapadi Anna Rumshisky and Adam Tauman Kalai. 2019. What's in a Name? Reducing Bias in Bios without Access to Protected Attributes. https://doi.org/10.48550/ARXIV.1904.05233 10.48550/ARXIV.1904.05233 · DOI
  49. Alexey Romanov Maria De-Arteaga Hanna Wallach Jennifer Chayes Christian Borgs Alexandra Chouldechova Sahin Geyik Krishnaram Kenthapadi Anna Rumshisky and Adam Tauman Kalai. 2019. What's in a Name? Reducing Bias in Bios without Access to Protected Attributes. https://doi.org/10.48550/ARXIV.1904.05233 · DOI
  50. Candace Ross , Boris Katz , and Andrei Barbu . 2021. Measuring Social Biases in Grounded Vision and Language Embeddings . In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics , Online , 998–1008. https://doi.org/10. 1865 3/v1/2021.naacl-main.78 10.18653/v1 Candace Ross, Boris Katz, and Andrei Barbu. 2021. Measuring Social Biases in Grounded Vision and Language Embeddings. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 998–1008. https://doi.org/10.18653/v1/2021.naacl-main.78 · DOI
  51. Sebastian Ruder , Ivan Vulić , and Anders Søgaard . 2022 . Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold . In Findings of the Association for Computational Linguistics: ACL 2022 . Association for Computational Linguistics, Dublin, Ireland, 2340–2354. https://doi.org/10. 18653/v1/2022.findings-acl.184 10.18653/v1 Sebastian Ruder, Ivan Vulić, and Anders Søgaard. 2022. Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, 2340–2354. https://doi.org/10.18653/v1/2022.findings-acl.184 · DOI
  52. Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , and Lea Frermann . 2022. Does Representational Fairness Imply Empirical Fairness? . In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022 . Association for Computational Linguistics , Online only, 81–95. https://aclanthology.org/2022.findings-aacl.8 Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, and Lea Frermann. 2022. Does Representational Fairness Imply Empirical Fairness?. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022. Association for Computational Linguistics, Online only, 81–95. https://aclanthology.org/2022.findings-aacl.8
  53. Karolina Stanczak and Isabelle Augenstein. 2021. A Survey on Gender Bias in Natural Language Processing. https://doi.org/10.48550/ARXIV.2112.14168 10.48550/ARXIV.2112.14168 · DOI
  54. Karolina Stanczak and Isabelle Augenstein. 2021. A Survey on Gender Bias in Natural Language Processing. https://doi.org/10.48550/ARXIV.2112.14168 · DOI
  55. Tony Sun , Andrew Gaut , Shirlyn Tang , Yuxin Huang , Mai ElSherief , Jieyu Zhao , Diba Mirza , Elizabeth Belding , Kai-Wei Chang , and William Yang Wang . 2019 . Mitigating Gender Bias in Natural Language Processing: Literature Review . In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics , Florence, Italy, 1630–1640. https://doi.org/10. 18653/v1/P 19 - 1159 10.18653/v1 Tony Sun, Andrew Gaut, Shirlyn Tang, Yuxin Huang, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, and William Yang Wang. 2019. Mitigating Gender Bias in Natural Language Processing: Literature Review. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 1630–1640. https://doi.org/10.18653/v1/P19-1159 · DOI
  56. Yi Chern Tan and L. Elisa Celis . 2019. Assessing Social and Intersectional Biases in Contextualized Word Representations . Curran Associates Inc., Red Hook, NY, USA. Yi Chern Tan and L. Elisa Celis. 2019. Assessing Social and Intersectional Biases in Contextualized Word Representations. Curran Associates Inc., Red Hook, NY, USA.
  57. Ivan Vulić , Simon Baker , Edoardo Maria Ponti , Ulla Petti, Ira Leviant, Kelly Wing, Olga Majewska, Eden Bar, Matt Malone, Thierry Poibeau, Roi Reichart, and Anna Korhonen. 2020 . Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity. Computational Linguistics 46, 4 (02 2020), 847–897. https://doi.org/10.1162/coli_a_00391 arXiv:https://direct.mit.edu/coli/article-pdf/46/4/847/1888287/coli_a_00391.pdf 10.1162/coli_a_00391 Ivan Vulić, Simon Baker, Edoardo Maria Ponti, Ulla Petti, Ira Leviant, Kelly Wing, Olga Majewska, Eden Bar, Matt Malone, Thierry Poibeau, Roi Reichart, and Anna Korhonen. 2020. Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity. Computational Linguistics 46, 4 (02 2020), 847–897. https://doi.org/10.1162/coli_a_00391 arXiv:https://direct.mit.edu/coli/article-pdf/46/4/847/1888287/coli_a_00391.pdf · DOI
  58. Jason Wei and Eugene Santos Jr .2020. Narrative Origin Classification of Israeli-Palestinian Conflict Texts. In The Thirty-Third International FLAIRS Conference. Jason Wei and Eugene Santos Jr.2020. Narrative Origin Classification of Israeli-Palestinian Conflict Texts. In The Thirty-Third International FLAIRS Conference.
  59. Robert Williamson and Aditya Menon . 2019 . Fairness risk measures . In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research , Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6786– 6797 . https://proceedings.mlr.press/v97/williamson19a.html Robert Williamson and Aditya Menon. 2019. Fairness risk measures. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6786–6797. https://proceedings.mlr.press/v97/williamson19a.html
  60. Sheng Zhang , Xin Zhang , Weiming Zhang , and Anders Søgaard . 2021 . Sociolectal Analysis of Pretrained Language Models . In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 4581–4588 . https://doi.org/10.18653/v1/2021.emnlp-main.375 10.18653/v1 Sheng Zhang, Xin Zhang, Weiming Zhang, and Anders Søgaard. 2021. Sociolectal Analysis of Pretrained Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 4581–4588. https://doi.org/10.18653/v1/2021.emnlp-main.375 · DOI
  61. Jieyu Zhao , Yichao Zhou , Zeyu Li , Wei Wang , and Kai-Wei Chang . 2018 . Learning Gender-Neutral Word Embeddings . In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics , Brussels, Belgium, 4847–4853. https://doi.org/10. 18653/v1/D 18 - 1521 10.18653/v1 Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang. 2018. Learning Gender-Neutral Word Embeddings. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 4847–4853. https://doi.org/10.18653/v1/D18-1521 · DOI

Cited by

Sorted by citations

Metadata

Authors
Cabello, L., Jørgensen, A. K., & Søgaard, A.
Affiliations
  • University of Copenhagen, Denmark
  • University of Copenhagen (DK)
ORCID
Venue
2023 ACM Conference on Fairness, Accountability, and Transparency
Publisher
ACM
Published
2023-06-12
Pages
370-378
DOI
10.1145/3593013.3594004
OpenAlex
W4380364765
Cited by
14
References
9
Citations by year
2026: 2 · 2025: 5 · 2024: 4 · 2023: 3
FWCI
2.99
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
Keywords
pre-trained language models, representation bias, bias metrics, fairness metrics, protected characteristics

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