Bergson: An Open Source Library for Data Attribution

dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale

Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-example gradients, whose computation and use at LLM scale pose challenges in efficiency, compatibility, and extensibility. We introduce dattri-LLM, a TDA library that makes...

WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing

When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer has failed or the model has learned a shortcut. We introduce WOMBAT, a benchmark of 14 whitebox GNNs, each with message-passing weights set by hand to detect a specific...

Traceprop: Training Data Attribution in a Single Pass

The contribution here is systems, not a new estimator: LogIX's attribution quality, in one pass instead of two, is systems, not a new estimator: LogIX's attribution quality, in one pass instead of two.

Form Over Content In Gradient-Based Data Attribution Methods

Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient similarity actually measures is debated. Some interpret it as identifying task-relevant skills, while other work reports that surface form is the main factor. We resolve th...

Can LLMs Serve as a Data Error Detection Engine? Trade-offs in Accuracy, Cost, and Hallucination Across Datasets

These findings endorse the viability of LLMs as a feasible alternative for data error detection; nonetheless, challenges such as hallucination and cost aspects remain, especially regarding the resources necessary for the effective implementation of these models in practical applications.

How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design