Analyze a tabular data model with LIT, including exploring partial dependence plots and automatically finding counterfactuals.

Analyze an image classification model with LIT, including multiple image salience techniques.

Use LIT with any of three tasks from the General Language Understanding Evaluation (GLUE) benchmark suite. This demo contains binary classification (for sentiment analysis, using SST2), multi-class classification (for textual entailment, using MultiNLI), and regression (for measuring text similarity, using STS-B).

Use LIT directly inside a Colab notebook. Explore binary classification for sentiment analysis using SST2 from the General Language Understanding Evaluation (GLUE) benchmark suite.

Use LIT to explore gendered associations in a coreference system, which matches pronouns to their antecedents. This demo highlights how LIT can work with structured prediction models (edge classification), and its capability for disaggregated analysis.

Explore a BERT-based masked-language model. See what tokens the model predicts should fill in the blank when any token from an example sentence is masked out.

Use a T5 model to summarize text. For any example of interest, quickly find similar examples from the training set, using an approximate nearest-neighbors index.

Explore the faithfulness of input salience methods on a BERT-base model across different datasets and artificial shortcuts.