Interpretability and mechanistic analysis · MLD-0648
LIME
Explaining a prediction using an interpretable surrogate fitted near the input.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Approximate a classifier locally with a linear model.
Original caveat
Explanations can be sensitive to perturbation and neighborhood choices.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: Local interpretable model-agnostic explanations.
Related concepts
Concepts linking here
Technology connections
- LIME — Local surrogate-model explanation toolkit.
Original references
- Captum model interpretability documentation ↗ · Reference link
- Tracing the thoughts of a large language model ↗ · Consulted
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning ↗ · Consulted
- SHAP documentation ↗ · Reference link
- Original reference URL ↗