# Robots Enact Malignant Stereotypes

arXiv: https://arxiv.org/abs/2207.11569 · HTML: https://mlsanity.com/paper/2207.11569/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 123 references that are in the map.
- First posted on arXiv 23 Jul 2022.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Transporter Networks: Rearranging the Visual World for Robotic Manipulation](https://mlsanity.com/paper/2010.14406/) (2020)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [The Values Encoded in Machine Learning Research](https://mlsanity.com/paper/2106.15590/) (2021)
- [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019)
- [Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning](https://mlsanity.com/paper/1912.10389/) (2019)
- [Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database](https://mlsanity.com/paper/2011.08512/) (2020)
- [Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing](https://mlsanity.com/paper/2001.00964/) (2020)
- [Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development](https://mlsanity.com/paper/2108.04308/) (2021)
- [Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research](https://mlsanity.com/paper/2011.14826/) (2020)
- [Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks](https://mlsanity.com/paper/2012.03385/) (2020)
- [Predictive Inequity in Object Detection](https://mlsanity.com/paper/1902.11097/) (2019)
- [SORNet: Spatial Object-Centric Representations for Sequential Manipulation](https://mlsanity.com/paper/2109.03891/) (2021)
- [Language Grounding with 3D Objects](https://mlsanity.com/paper/2107.12514/) (2021)
- [A Data-Driven Analysis of Workers' Earnings on Amazon Mechanical Turk](https://mlsanity.com/paper/1712.05796/) (2017)
- [Fast Policy Learning through Imitation and Reinforcement](https://mlsanity.com/paper/1805.10413/) (2018)
- [Diversity and Inclusion Metrics in Subset Selection](https://mlsanity.com/paper/2002.03256/) (2020)
- [Value Cards: An Educational Toolkit for Teaching Social Impacts of Machine Learning through Deliberation](https://mlsanity.com/paper/2010.11411/) (2020)
- [Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement](https://mlsanity.com/paper/2111.07975/) (2021)

## Built on by (most cited first, 14 of 14)

- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges](https://mlsanity.com/paper/2501.02189/) (2025)
- [Generating Robot Constitutions & Benchmarks for Semantic Safety](https://mlsanity.com/paper/2503.08663/) (2025)
- [LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions](https://mlsanity.com/paper/2406.08824/) (2024)
- [SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation](https://mlsanity.com/paper/2401.08053/) (2024)
- [Ethical Considerations for Responsible Data Curation](https://mlsanity.com/paper/2302.03629/) (2023)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [A Taxonomy of Challenges to Curating Fair Datasets](https://mlsanity.com/paper/2406.06407/) (2024)
- [Encoding Inequity: Examining Demographic Bias in LLM-Driven Robot Caregiving](https://mlsanity.com/paper/2503.05765/) (2025)
- [RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation](https://mlsanity.com/paper/2508.21378/) (2025)
- [Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety](https://mlsanity.com/paper/2509.02163/) (2025)
- [A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts](https://mlsanity.com/paper/2509.18177/) (2025)
- [Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction](https://mlsanity.com/paper/2607.06344/) (2026)
- [LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark](https://mlsanity.com/paper/2609.00192/) (2026)

## Abstract (arXiv)

Stereotypes, bias, and discrimination have been extensively documented in Machine Learning (ML) methods such as Computer Vision (CV) [18, 80], Natural Language Processing (NLP) [6], or both, in the case of large image and caption models such as OpenAI CLIP [14]. In this paper, we evaluate how ML bias manifests in robots that physically and autonomously act within the world. We audit one of several recently published CLIP-powered robotic manipulation methods, presenting it with objects that have pictures of human faces on the surface which vary across race and gender, alongside task descriptions that contain terms associated with common stereotypes. Our experiments definitively show robots acting out toxic stereotypes with respect to gender, race, and scientifically-discredited physiognomy, at scale. Furthermore, the audited methods are less likely to recognize Women and People of Color. Our interdisciplinary sociotechnical analysis synthesizes across fields and applications such as Science Technology and Society (STS), Critical Studies, History, Safety, Robotics, and AI. We find that robots powered by large datasets and Dissolution Models (sometimes called "foundation models", e.g. CLIP) that contain humans risk physically amplifying malignant stereotypes in general; and that merely correcting disparities will be insufficient for the complexity and scale of the problem. Instead, we recommend that robot learning methods that physically manifest stereotypes or other harmful outcomes be paused, reworked, or even wound down when appropriate, until outcomes can be proven safe, effective, and just. Finally, we discuss comprehensive policy changes and the potential of new interdisciplinary research on topics like Identity Safety Assessment Frameworks and Design Justice to better understand and address these harms.