mlsanityData to 7 Oct 2026

Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation

arXiv 2402.01705 ↗First posted 25 Jan 2024cs.CY cs.AI cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

Algorithmic harms are commonly categorized as either allocative or representational. This study specifically addresses the latter, focusing on an examination of current definitions of representational harms to discern what is included and what is not. This analysis motivates our expansion beyond behavioral definitions to encompass harms to cognitive and affective states. The paper outlines high-level requirements for measurement: identifying the necessary expertise to implement this approach and illustrating it through a case study. Our work highlights the unique vulnerabilities of large language models to perpetrating representational harms, particularly when these harms go unmeasured and unmitigated. The work concludes by presenting proposed mitigations and delineating when to employ them. The overarching aim of this research is to establish a framework for broadening the definition of representational harms and to translate insights from fairness research into practical measurement and mitigation praxis.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 26 of its 152 references that are in the map. First posted on arXiv 25 Jan 2024.

Builds on

26 of 152 references.

References · 26

  1. 2021Ethical and social risks of harm from Language Modelscited by 957
  2. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  3. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  4. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  5. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  6. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  7. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  8. 2022Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reductioncited by 137
  9. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  10. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  11. 2023Evaluating the Social Impact of Generative AI Systems in Systems and Societycited by 91
  12. 2023"I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generationcited by 56
14 more
  1. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  2. 2023Supporting Human-AI Collaboration in Auditing LLMs with LLMscited by 46
  3. 2021Explainability Pitfalls: Beyond Dark Patterns in Explainable AIcited by 36
  4. 2022Measuring Representational Harms in Image Captioningcited by 36
  5. 2023An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Modelscited by 24
  6. 2023Taxonomizing and Measuring Representational Harms: A Look at Image Taggingcited by 24
  7. 2021Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agencycited by 22
  8. 2022Joint Multisided Exposure Fairness for Recommendationcited by 22
  9. 2022Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harmscited by 10
  10. 2022FairDistillation: Mitigating Stereotyping in Language Modelscited by 8
  11. 2022Richer Countries and Richer Representationscited by 7
  12. 2023Run Like a Girl! Sports-Related Gender Bias in Language and Visioncited by 6
  13. 2022Subverting Fair Image Search with Generative Adversarial Perturbationscited by 5
  14. 2022Experimental Evaluation of Baselines for Forecasting Social Media Timeseriescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 12; 2026: 2.

17 papers.

Sort:

By area:

  1. 2024Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLPcited by 22
  2. 2025Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)cited by 19
  3. 2025The Case for "Thick Evaluations" of Cultural Representation in AIcited by 16
  4. 2024What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Studycited by 15
  5. 2025A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologiescited by 14
  6. 2025Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systemscited by 11
  7. 2025From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphorscited by 9
  8. 2025Taxonomizing Representational Harms using Speech Act Theorycited by 7
  9. 2025Benchmarking Overton Pluralism in LLMscited by 7
  10. 2025More of the Same: Persistent Representational Harms Under Increased Representationcited by 6
  11. 2024Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Wayscited by 4
  12. 2025Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluationscited by 4
5 more
  1. 2025Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theorycited by 3
  2. 2025What Is the Point of Equality in Machine Learning Fairness? Beyond Equality of Opportunitycited by 1
  3. 2025Bayesian Network Fusion of Large Language Models for Sentiment Analysiscited by 0
  4. 2026A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictionscited by 0
  5. 2026A Roadmap to Impactful Pluralistic Alignment Researchcited by 0