Peter Pham

Peter Pham

Senior Program Manager at Applause

    Peter is a Senior Program Manager at Applause. He manages architecting data pipelines for LLMs and AI models. He leads cross-functional teams to curate & refine training data, ensuring models learn from the best sources. Peter is passionate about ethical & responsible AI development.

    All Sessions by Peter Pham

    Day 2 04/24/2024
    2:00 pm - 2:30 pm

    Overcoming the Limitations of LLM Safety Parameters with Human Testing and Monitoring

    <span class="etn-schedule-location"> <span class="firstfocus">ML Safety & Security</span>

    Ensuring safety, fairness, and responsibility has become a critical challenge in the rapidly evolving landscape of Large Language Models (LLMs). This talk delves into a new approach to address these concerns by leveraging the power of human testing and monitoring from a diverse global population. We present a comprehensive strategy employing a combination of crowd-sourced and professional testers from various locations, countries, cultures, and life experiences. Our approach thoroughly scrutinizes LLM and LLM application input and output spaces. It ensures responsible and safe product delivery. The presentation centers on functional performance, usability, accessibility, and bug testing. We share our research into these approaches and include recommendations for building test plans, adversarial testing approaches, and real-world usage scenarios. This diverse, global, human-based testing approach is a direct solution to the issues raised in recent papers highlighting the limited effectiveness of RLHF-created safety parameters against fine-tuning and prompt injection. Experts are calling for LLMs that inject safety parameters at the base parameter level, but, to date, this has resulted in a significant drop in LLM efficacy. Additionally, building safety directly into the pre-trained model is prohibitively expensive. Our approach overcomes these technical and financial limitations and is applicable now. Results point to a paradigm shift in LLM safety practices, yielding models and applications that remain helpful and harmless throughout their lifecycle.

    Open Data Science




    Open Data Science
    One Broadway
    Cambridge, MA 02142

    Privacy Settings
    We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
    Consent to display content from - Youtube
    Consent to display content from - Vimeo
    Google Maps
    Consent to display content from - Google