[2406.17583] Towards Compositional Interpretability for XAI

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2406.17583] Towards Compositional Interpretability for XAI --> Computer Science > Artificial Intelligence arXiv:2406.17583 (cs) [Submitted on 25 Jun 2024] Title: Towards Compositional Interpretability for XAI Authors: Sean Tull , Robin Lorenz , Stephen Clark , Ilyas Khan , Bob Coecke View a PDF of the paper titled Towards Compositional Interpretability for XAI, by Sean Tull and 4 other authors View PDF Abstract: Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this maj

saved by

• Barton Rhodes

related reading

• Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
• Transformer Circuits Threadtransformer-circuits.pub
• The Hitchhiker's Guide to Actionable Interpretabilityactionable-interpretability-guide.github.io
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• On Optimism for Interpretabilitygoodfire.ai
• An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
• The Building Blocks of Interpretabilitydistill.pub
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• How Can Interpretability Researchers Help AGI Go Well? — AI Alignment Forumalignmentforum.org
• Intentionally Designing the Future of AIgoodfire.ai
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org