Interpretability via Symbolic Distillation

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,600
Published on ● Video Link: https://www.youtube.com/watch?v=XHBJJ2N-kUc


Duration: 51:04
1,277 views
42

Miles Cranmer (Flatiron Institute)
https://simons.berkeley.edu/talks/miles-cranmer-flatiron-institute-2023-08-15
Large Language Models and Transformers



Other Videos By Simons Institute for the Theory of Computing


2023-08-18Integrating Language into Intelligent Architectures
2023-08-17Meaning in the age of large language models
2023-08-17Formalizing Explanations of Neural Network Behaviors
2023-08-17Are Aligned Language Models “Adversarially Aligned”?
2023-08-17Language Models as Statisticians, and as Adapted Organisms
2023-08-17On Localization in Language Models
2023-08-17Panel Discussion
2023-08-16Large Language Models Meet Copyright Law
2023-08-16How to Use Self-Play for Language Models to Improve at Solving Programming Puzzles
2023-08-16Build an Ecosystem, Not a Monolith
2023-08-16Interpretability via Symbolic Distillation
2023-08-16A Theory for Emergence of Complex Skills in Language Models
2023-08-16Scaling Data-Constrained Language Models
2023-08-15Understanding the Origins and Taxonomy of Neural Scaling Laws
2023-08-15Panel Discussion
2023-08-14An observation on Generalization
2023-08-14Towards Reliable Use of Large Language Models: Better Detection, Consistency, and Instruction-Tuning
2023-08-14Possible Impossibilities and Impossible Possibilities
2023-08-14Sparks of Artificial General Intelligence
2023-08-10Generating Approximate Ground States of Molecules Using Quantum Machine Learning
2023-08-10Quantum-Classical Cross-Correlations and the Post-selection Problem


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Large Language Models and Transformers
Miles Cranmer