Paper: Troubling Taxonomies in GenAI Evaluation

A paper by MINT Lab affiliates Ned Cooper and Glen Berman, along with co-authors Wesley Hanwen Deng and Ben Hutchinson, was accepted for poster presentation in the NeurIPS Workshop on Evaluating Evaluations: Examining Best Practices for Measuring Broader Impacts of Generative AI.

Abstract: To evaluate the societal impacts of GenAI requires a model of how social harms emerge from interactions between GenAI, people, and societal structures. Yet a model is rarely explicitly defined in societal impact evaluations, or in the taxonomies of societal impacts that support them. In this provocation, we argue that societal impacts should be conceptualised as application- and context-specific, incommensurable, and shaped by questions of social power. Doing so leads us to conclude that societal impact evaluations using existing taxonomies are inherently limited, in terms of their potential to reveal how GenAI systems may interact with people when introduced into specific social contexts. We therefore propose a governance-first approach to managing societal harms attended by GenAI technologies.

Read the full paper paper here.