pith. sign in

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2024 1 2023 1

representative citing papers

Localizing Model Behavior with Path Patching

cs.LG · 2023-04-12 · unverdicted · novelty 8.0

Path patching provides a method to express and quantitatively test hypotheses that neural network behaviors are localized to sets of paths.

How to use and interpret activation patching

cs.LG · 2024-04-23 · accept · novelty 5.0

Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.

citing papers explorer

Showing 2 of 2 citing papers.

  • Localizing Model Behavior with Path Patching cs.LG · 2023-04-12 · unverdicted · none · ref 39

    Path patching provides a method to express and quantitatively test hypotheses that neural network behaviors are localized to sets of paths.

  • How to use and interpret activation patching cs.LG · 2024-04-23 · accept · none · ref 7

    Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.