quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
cs.LG, cs.AI
Submitted: 2024-10-09
Updated: 2026-11-16
Code: https://github.com/dilyabareeva/quanda
Terminology
Sources
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Concept-based Explainable Artificial Intelligence: A Survey
- Training Data Attribution via Approximate Unrolled Differentiation
- Revisiting Methods for Finding Influential Examples
- A Simple and Efficient Baseline for Data Attribution on Images
- Captum: A unified and generic model interpretability library for PyTorch
- InterpretML: A Unified Framework for Machine Learning Interpretability
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis