CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions

Excerpt

arXiv:2406.12150v2 Announce Type: replace-cross Abstract: Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative features is difficult because real datasets rarely provide reliable ground truth. We introduce a multimodal benchmark containing symbolic tabular, vision, and audio tasks with known informative feature sets. In the main benchmark conditions, informative variables, spatial regions, or channels occupy