Auditing NLP systems for computational harms like surfacing stereotypes is an elusive goal. Several recent efforts have focused on benchmark datasets consisting of pairs of contrastive sentences, which are often accompanied by metrics that aggregate an NLP system’s behavior on these pairs into measurements of harms. We examine four such benchmarks constructed for two NLP tasks: language modeling and coreference resolution. We apply a measurement modeling lens—originating from the social sciences—to inventory a range of pitfalls that threaten these benchmarks’ validity as measurement models for stereotyping. We find that these benchmarks frequently lack clear articulations of what is being measured, and we highlight a range of ambiguities and unstated assumptions that affect how these benchmarks conceptualize and operationalize stereotyping.

A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors. While correctly interpreting and assessing the effects of such adjective-noun pairs (e.g., false key) on the plausibility of given events (e.g., opening doors) underpins many natural language understanding tasks, doing so often requires a significant degree of world knowledge and common-sense reasoning. We introduce ADEPT – a large-scale semantic plausibility task consisting of over 16 thousand sentences that are paired with slightly modified versions obtained by adding an adjective to a noun. Overall, we find that while the task appears easier for human judges (85% accuracy), it proves more difficult for transformer-based models like RoBERTa (71% accuracy). Our experiments also show that neither the adjective itself nor its taxonomic class suffice in determining the correct plausibility judgement, emphasizing the importance of endowing automatic natural language understanding systems with more context sensitivity and common-sense reasoning.