#model-explanation News & Analysis

2 articles tagged with #model-explanation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AINeutralarXiv – CS AI · Apr 147/10

🧠

Regional Explanations: Bridging Local and Global Variable Importance

Researchers identify fundamental flaws in Local Shapley Values and LIME, two widely-used machine learning interpretation methods that fail to reliably detect locally important features. They propose R-LOCO, a new approach that bridges local and global explanations by segmenting input space into regions and applying global attribution methods within those regions for more faithful local attributions.

AINeutralarXiv – CS AI · Jun 236/10

🧠

Cross-Attention is Half Explanation in Speech-to-Text Models

Researchers find that cross-attention mechanisms in speech-to-text models only explain about 50% of how the decoder attends to input, contradicting widespread assumptions that attention scores reliably indicate which parts of the audio are most relevant. The study across multiple model scales shows attention provides an incomplete view of the factors driving predictions.