[2109.03853] A Bayesian Framework for Information-Theoretic Probing
YOU make open access possible! Tell us why you support #openaccess and give to arXiv this week to help keep science open for all. Help | Advanced Search 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
[2109.03853] A Bayesian Framework for Information-Theoretic Probing Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2109.03853 (cs) [Submitted on 8 Sep 2021] Title: A Bayesian Framework for Information-Theoretic Probing Authors: Tiago Pimentel , Ryan Cotterell View a PDF of the paper titled A Bayesian Framework for Information-Theoretic Probing, by Tiago Pimentel and 1 other authors View PDF Abstract: Pimentel et al. (2020) recently analysed probing f
Explore this link on the map →related reading
- Visual Information Theory -- colah's blogcolah.github.io
- Bayesian programming - Wikipediaen.wikipedia.org
- [2006.00995] Amnesic Probing: Behavioral Explanation with Amnesic Counterfactualsarxiv.org
- [2002.10689] A Theory of Usable Information Under Computational Constraintsarxiv.org
- Learning to be Bayesian without Supervisionpapers.nips.cc
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- How well do truth probes generalise? — LessWronglesswrong.com
- Teaching LLMs to reason like Bayesiansresearch.google
- book.pdfinference.org.uk
- [physics/0004057] 1 Introductionar5iv.labs.arxiv.org
- How does in-context learning work? A framework for understanding the differences from traditional supervised learning | SAIL Blogai.stanford.edu
- How And Why To Learn Bayesian Inference | Towards Data Sciencetowardsdatascience.com