Skip to content
conftrace_

model debugging

27 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model interpretability (7) influence function (7) training data (4) spurious correlation (3) feature attribution (3) computer vision (3) out-of-distribution detection (2) training data attribution (2) vision-language model (2) large language model (2)

Papers

Semantically Equivalent Adversarial Rules for Debugging NLP models ACL 2018 Understanding Black-box Predictions via Influence Functions ICML 2017