1 个仓库
Awesome GitHub RepositoriesReference Datapoint Comparisons
Comparing a specific model prediction against a pinned reference example to analyze behavioral variance.
Distinct from Model Comparison Interfaces: Distinct from Model Comparison Interfaces: focuses on comparing different datapoints for one or more models rather than just comparing different models.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Reference Datapoint Comparisons. Refine with filters or upvote what's useful.
Awesome Reference Datapoint Comparisons GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- pair-code/lit
PAIR-code/lit
3,636在 GitHub 上查看Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable
Allows pinning a reference datapoint to visualize how model behavior differs relative to a primary selection.
TypeScriptmachine-learningnatural-language-processingvisualization
