12 accepted papers
In this position paper we argue that conclusions drawn about relative system safety or attack method efficacy via AI red teaming are often not supported by evidence provided by attack success rate (ASR) comparisons. We show, through conceptual, theoretical, and empirical contributions, that many c…
"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific infor…
The measurement tasks involved in evaluating generative AI (GenAI) systems lack sufficient scientific rigor, leading to what has been described as "a tangle of sloppy tests [and] apples-to-oranges comparisons" (Roose, 2024). In this position paper, we argue that the ML community would benefit from l…
Representational harms are widely recognized among fairness-related harms caused by generative language systems. However, their definitions are commonly under-specified. We make a theoretical contribution to the specification of representational harms by introducing a framework, grounded in speech a…
The NLP research community has made publicly available numerous instruments for measuring representational harms caused by large language model (LLM)-based systems. These instruments have taken the form of datasets, metrics, tools, and more. In this paper, we examine the extent to which such instrum…
The LLM-as-a-judge paradigm, in which a judge LLM system replaces human raters in rating the outputs of other generative AI (GenAI) systems, plays a critical role in scaling and standardizing GenAI evaluations. To validate such judge systems, evaluators assess human--judge agreement by first collect…
Disaggregated evaluation—estimation of performance of a machine learning model on different subpopulations—is a core task when assessing performance and group-fairness of AI systems. A key challenge is that evaluation data is scarce, and subpopulations arising from intersections of attri…
"We introduce Semi-supervised Performance Evaluation for Face Recognition (SPE-FR). SPE-FR is a statistical method for evaluating the performance and algorithmic bias of face verification systems when identity labels are unavailable or incomplete. The method is based on parametric Bayesian modeling…
Algorithmic risk assessments are used to inform decisions in a wide variety of high-stakes settings. Often multiple predictive models deliver similar overall performance but differ markedly in their predictions for individual cases, an empirical phenomenon known as the “Rashomon Effect.” These model…
Algorithms are commonly used to predict outcomes under a particular decision or intervention, such as predicting likelihood of default if a loan is approved. Generally, to learn such counterfactual prediction models from observational data on historical decisions and corresponding outcomes, one mus…
Risk assessment tools are widely used around the country to inform decision making within the criminal justice system. Recently, considerable attention has been devoted to the question of whether such tools may suffer from racial bias. In this type of assessment, a fundamental issue is that the trai…
Following precedent in employment discrimination law, two notions of disparity are widely-discussed in papers on fairness and ML. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups differently; algorithms exhibit impact disparity when outcomes differ across…