Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation

Abstract

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.

23 pages, 7 figures

References in corpus (6)

• Gender bias and stereotypes in Large Language Models
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
• AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia
• Supporting Human-AI Collaboration in Auditing LLMs with LLMs
• Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency
• Subverting Fair Image Search with Generative Adversarial Perturbations

Cited by in corpus (4)

• Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)
• From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors
• A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologies
• AI Language Models Could Both Help and Harm Equity in Marine Policymaking: The Case Study of the BBNJ Question-Answering Bot