It is increasingly common to evaluate the same coreference resolution (CR) model on multiple datasets. Do these multi-dataset evaluations allow us to draw meaningful conclusions about model generalization? Or, do they rather reflect the idiosyncrasies of a particular experimental setup (e.g., the specific datasets used)? To study this, we view evaluation through the lens of measurement modeling, a framework commonly used in the social sciences for analyzing the validity of measurements. By taking this perspective, we show how multi-dataset evaluations risk conflating different factors concerning what, precisely, is being measured. This in turn makes it difficult to draw more generalizable conclusions from these evaluations. For instance, we show that across seven datasets, measurements intended to reflect CR model generalization are often correlated with differences in both how coreference is defined and how it is operationalized; this limits our ability to draw conclusions regarding the ability of CR models to generalize across any singular dimension. We believe the measurement modeling framework provides the needed vocabulary for discussing challenges surrounding what is actually being measured by CR evaluations.

Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to behave identically for social groups, to adaptation, where behaviors should instead vary across them. To illuminate tensions around invariance and adaptation, we conduct five case studies, in which we perturb different types of identity-related language features (names, roles, locations, dialect, and style) in NLG system inputs. Through these cases studies, we examine people’s expectations of system behaviors, and surface potential caveats of these contrasting yet commonly held assumptions. We find that motivations for adaptation include social norms, cultural differences, feature-specific information, and accommodation; in contrast, motivations for invariance include perspectives that favor prescriptivism, view adaptation as unnecessary or too difficult for NLG systems to do appropriately, and are wary of false assumptions. Our findings highlight open challenges around what constitute “fair” or “good” NLG system behaviors.

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark’s measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices—e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks’ measurements.

It is critical to measure and mitigate fairness-related harms caused by AI text generation systems, including stereotyping and demeaning harms. To that end, we introduce FairPrism, a dataset of 5,000 examples of AI-generated English text with detailed human annotations covering a diverse set of harms relating to gender and sexuality. FairPrism aims to address several limitations of existing datasets for measuring and mitigating fairness-related harms, including improved transparency, clearer specification of dataset coverage, and accounting for annotator disagreement and harms that are context-dependent. FairPrism’s annotations include the extent of stereotyping and demeaning harms, the demographic groups targeted, and appropriateness for different applications. The annotations also include specific harms that occur in interactive contexts and harms that raise normative concerns when the “speaker” is an AI system. Due to its precision and granularity, FairPrism can be used to diagnose (1) the types of fairness-related harms that AI text generation systems cause, and (2) the potential limitations of mitigation methods, both of which we illustrate through case studies. Finally, the process we followed to develop FairPrism offers a recipe for building improved datasets for measuring and mitigating harms caused by AI systems.

Many state-of-the-art natural language understanding (NLU) models are based on pretrained neural language models. These models often make inferences using information from multiple sources. An important class of such inferences are those that require both background knowledge, presumably contained in a model’s pretrained parameters, and instance-specific information that is supplied at inference time. However, the integration and reasoning abilities of NLU models in the presence of multiple knowledge sources have been largely understudied. In this work, we propose a test suite of coreference resolution subtasks that require reasoning over multiple facts. These subtasks differ in terms of which knowledge sources contain the relevant facts. We also introduce subtasks where knowledge is present only at inference time using fictional knowledge. We evaluate state-of-the-art coreference resolution models on our dataset. Our results indicate that several models struggle to reason on-the-fly over knowledge observed both at pretrain time and at inference time. However, with task-specific training, a subset of models demonstrates the ability to integrate certain knowledge types from multiple sources. Still, even the best performing models seem to have difficulties with reliably integrating knowledge presented only at inference time.

AI and NLP publication venues have increasingly encouraged researchers to reflect on possible ethical considerations, adverse impacts, and other responsible AI issues their work might engender. However, for specific NLP tasks our understanding of how prevalent such issues are, or when and why these issues are likely to arise, remains limited. Focusing on text summarization—a common NLP task largely overlooked by the responsible AI community—we examine research and reporting practices in the current literature. We conduct a multi-round qualitative analysis of 333 summarization papers from the ACL Anthology published between 2020–2022. We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals. We also discuss current evaluation practices and consider how authors discuss the limitations of both prior work and their own work. Overall, we find that relatively few papers engage with possible stakeholders or contexts of use, which limits their consideration of potential downstream adverse impacts or other responsible AI issues. Based on our findings, we make recommendations on concrete practices and research directions.

There are many ways to express similar things in text, which makes evaluating natural language generation (NLG) systems difficult. Compounding this difficulty is the need to assess varying quality criteria depending on the deployment setting. While the landscape of NLG evaluation has been well-mapped, practitioners’ goals, assumptions, and constraints—which inform decisions about what, when, and how to evaluate—are often partially or implicitly stated, or not stated at all. Combining a formative semi-structured interview study of NLG practitioners (N=18) with a survey study of a broader sample of practitioners (N=61), we surface goals, community practices, assumptions, and constraints that shape NLG evaluations, examining their implications and how they embody ethical considerations.

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.