The Reasonable Effectiveness of Diverse Evaluation Data

In this paper, we present findings from an semi-experimental exploration of rater diversity and its influence on safety annotations of conversations generated by humans talking to a generative AI-chat bot. We find significant differences in judgments produced by raters from different geographic regions and annotation platforms, and correlate these perspectives with demographic sub-groups. Our work helps define best practices in model development -- specifically human evaluation of generative models -- on the backdrop of growing work on sociotechnical AI evaluations.