Explainability
Causal Pathways
Shows how effects propagate through the model
4 techniques in this subcategory
4 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Sobol Indices | Algorithmic | Architecture/model Agnostic Requirements/black Box | Tabular | Sobol indices show how much of the variation in a model's output can be traced to each of its inputs. The analyst sets a... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +5 | Any | Influence functions estimate which training examples most affected a model's prediction on a particular test example.... | ||
| Causal Mediation Analysis in Language Models | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +3 | Text | Causal mediation analysis traces which internal components of a language model carry the effect of a change in the input... | ||
| Concept Activation Vectors | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | A concept activation vector (CAV) is a direction inside a neural network that stands for a human idea such as 'stripes'.... |
Rows per page
Page 1 of 1