Logo: University of Southern California

Events Calendar


  • AI Seminar- Composable Interventions for Language Models

    Fri, Aug 09, 2024 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Arinbjorn Kolbeinsson, University of Virginia

    Talk Title: Composable Interventions for Language Models

    Abstract: Virtual zoom link: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645Meeting ID: 704 285 0182Meeting password: 832239
    Abstract: Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories — Knowledge Editing, Model Compression, and Machine Unlearning. Our results from 310 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. All of our code is public: https://github.com/hartvigsen-group/composable-interventions

    Biography: Arinbjörn Kolbeinsson is currently serving as a visiting scholar at the University of Virginia, focusing on responsible and accurate models for health and biomedicine. His recent research explores the editing and efficiency of language models, along with the development of composable intervention techniques. Previously, Arinbjörn was a machine learning scientist at Evidation Health Inc., where he developed innovative methods to predict health outcomes using high-frequency multi-modal data. His work was pivotal in advancing differential privacy, disease modeling, and reinforcement learning for health applications. Arinbjörn completed his Ph.D. in Biostatistics at Imperial College London in 2020, specializing in deep learning for health outcome prediction.

    Host: Abel Salinas and Maura Covaci

    More Info: https://www.isi.edu/events/5056/composable-interventions-for-language-models/

    Webcast: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645

    Location: Information Science Institute (ISI) - Virtual Only

    WebCast Link: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645

    Audiences: Everyone Is Invited

    Contact: Pete Zamar

    Event Link: https://www.isi.edu/events/5056/composable-interventions-for-language-models/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File

Return to Calendar