# Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation

arXiv: https://arxiv.org/abs/2402.01705 · HTML: https://mlsanity.com/paper/2402.01705/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 152 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Evaluating the Social Impact of Generative AI Systems in Systems and Society](https://mlsanity.com/paper/2306.05949/) (2023)
- ["I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation](https://mlsanity.com/paper/2305.09941/) (2023)
- [AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia](https://mlsanity.com/paper/2305.11844/) (2023)
- [Supporting Human-AI Collaboration in Auditing LLMs with LLMs](https://mlsanity.com/paper/2304.09991/) (2023)
- [Explainability Pitfalls: Beyond Dark Patterns in Explainable AI](https://mlsanity.com/paper/2109.12480/) (2021)
- [Measuring Representational Harms in Image Captioning](https://mlsanity.com/paper/2206.07173/) (2022)
- [Taxonomizing and Measuring Representational Harms: A Look at Image Tagging](https://mlsanity.com/paper/2305.01776/) (2023)
- [An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models](https://mlsanity.com/paper/2301.09211/) (2023)
- [Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency](https://mlsanity.com/paper/2105.08667/) (2021)
- [Joint Multisided Exposure Fairness for Recommendation](https://mlsanity.com/paper/2205.00048/) (2022)
- [Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harms](https://mlsanity.com/paper/2204.13568/) (2022)
- [FairDistillation: Mitigating Stereotyping in Language Models](https://mlsanity.com/paper/2207.04546/) (2022)
- [Richer Countries and Richer Representations](https://mlsanity.com/paper/2205.05093/) (2022)
- [Run Like a Girl! Sports-Related Gender Bias in Language and Vision](https://mlsanity.com/paper/2305.14468/) (2023)
- [Subverting Fair Image Search with Generative Adversarial Perturbations](https://mlsanity.com/paper/2205.02414/) (2022)
- [Experimental Evaluation of Baselines for Forecasting Social Media Timeseries](https://mlsanity.com/paper/2210.05847/) (2022)

## Built on by (most cited first, 17 of 17)

- [Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP](https://mlsanity.com/paper/2405.17159/) (2024)
- [Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)](https://mlsanity.com/paper/2505.21091/) (2025)
- [The Case for "Thick Evaluations" of Cultural Representation in AI](https://mlsanity.com/paper/2503.19075/) (2025)
- [What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study](https://mlsanity.com/paper/2410.00545/) (2024)
- [A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologies](https://mlsanity.com/paper/2502.09870/) (2025)
- [Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems](https://mlsanity.com/paper/2502.14019/) (2025)
- [From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors](https://mlsanity.com/paper/2501.18045/) (2025)
- [Taxonomizing Representational Harms using Speech Act Theory](https://mlsanity.com/paper/2504.00928/) (2025)
- [Benchmarking Overton Pluralism in LLMs](https://mlsanity.com/paper/2512.01351/) (2025)
- [More of the Same: Persistent Representational Harms Under Increased Representation](https://mlsanity.com/paper/2503.00333/) (2025)
- [Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Ways](https://mlsanity.com/paper/2402.04420/) (2024)
- [Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations](https://mlsanity.com/paper/2511.05613/) (2025)
- [Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory](https://mlsanity.com/paper/2510.13902/) (2025)
- [What Is the Point of Equality in Machine Learning Fairness? Beyond Equality of Opportunity](https://mlsanity.com/paper/2506.16782/) (2025)
- [Bayesian Network Fusion of Large Language Models for Sentiment Analysis](https://mlsanity.com/paper/2510.26484/) (2025)
- [A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions](https://mlsanity.com/paper/2606.14460/) (2026)
- [A Roadmap to Impactful Pluralistic Alignment Research](https://mlsanity.com/paper/2607.22305/) (2026)

## 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.