conftrace_

input attribution

7 papers

Explore in graph

Also known as

IA

Co-occurring keywords · papers mentioning both

integrated gradient (4) gradient-based method (2) model interpretability (2) meme offensiveness detection (1) multi-step filtering (1) network compression (1) neural network explanation (1) gradient-based attribution (1) meme detection (1) token interaction (1)

Papers

Can Input Attributions Explain Inductive Reasoning in In-Context Learning? ACL 2025 SEMANTIFY: Unveiling Memes with Robust Interpretability beyond Input Attribution IJCAI 2024 Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling ICCV 2023 Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network NeurIPS 2022 Explaining Classes through Stable Word Attributions ACL 2022 Measuring the Mixing of Contextual Information in the Transformer EMNLP 2022 Attribution Preservation in Network Compression for Reliable Network Interpretation NeurIPS 2020