"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 information from a generative-AI model's parameters, e.g., a particular individual's personal data or the inclusion of copyrighted content in the model's training data. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs, e.g., generations that closely resemble a particular individual's data or reflect the concept of "Spiderman." Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges. We provide a framework for ML researchers and policymakers to think rigorously about these challenges, identifying several mismatches between the goals of unlearning and feasible implementations. These mismatches explain why unlearning is not a general-purpose solution for circumscribing generative-AI model behavior in service of broader positive impact.

Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions. We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification.

This paper examines the tensions between neighborhood gentrification and community surveillance posts on Nextdoor, a hyperlocal social media platform for neighborhoods. We created a privacy-preserving pipeline to gather research data from public Nextdoor posts in Atlanta, Georgia and filtered these to a dataset of 1,537 community surveillance posts. We developed a qualitative codebook to label observed patterns of community surveillance, and deploy a large language model to tag these posts at scale. Ultimately, we present an extensible and empirically-tested typology of the modes of community surveillance that occur on hyperlocal platforms. We find a complex relationship between community surveillance posts and neighborhood gentrification, which indicates that publicly disclosing information about perceived outsiders, especially for petty crimes, is most prevalent in gentrifying neighborhoods. Our empirical evidence inform critical perspectives which posit that community surveillance on platforms like Nextdoor can exclude and marginalize minoritized populations, particularly in gentrifying neighborhoods. Our findings carry broader implications for hyperlocal social platforms and their potential to amplify and exacerbate social tensions and exclusion.

Tong Chen, Akari Asai, Niloofar Mireshghallah, Sewon Min, James Grimmelmann, Yejin Choi, Hannaneh Hajishirzi, Luke Zettlemoyer, Pang Wei Koh. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

The increasing harms caused by hate, harassment, and other forms of abuse online have motivated major platforms to explore hierarchical governance. The idea is to allow communities to have designated members take on moderation and leadership duties; meanwhile, members can still escalate issues to the platform. But these promising approaches have only been explored in plaintext settings where community content is public to the platform. It is unclear how one can realize hierarchical governance in the huge and increasing number of online communities that utilize end-to-end encrypted (E2EE) messaging for privacy.We propose private hierarchical governance systems. These should enable similar levels of community governance as in plaintext settings, while maintaining cryptographic privacy of content and governance actions not reported to the platform. We design the first such system, taking a layered approach that adds governance logic on top of an encrypted messaging protocol; we show how an extension to the message layer security (MLS) protocol suffices for achieving a rich set of governance policies. Our approach allows developers to rapidly prototype new governance features, taking inspiration from a plaintext system called PolicyKit. We build a prototype E2EE messaging system called MlsGov that supports content-based community and platform moderation, elections of community moderators, votes to remove abusive users, and more.