Optimal ablation for interpretability
Interpretability studies often involve tracing the flow of information through machine learning models to identify specific model components that perform relevant computations for tasks of interest. Prior work quantifies the importance of a model component on a particular task by measuring the impact of performing ablation on that component, or simulating model inference with the component disabled. We propose a new method, optimal ablation (OA), and show that OA-based component importance has theoretical and empirical advantages over measuring importance via other ablation methods. We also show that OA-based component importance can benefit several downstream interpretability tasks, including circuit discovery, localization of factual recall, and latent prediction.
Code (1)
Similar Papers 제목 키워드 기반
Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation
This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental…
Cross-Modal RetrievalMedical priority fusion: achieving dual optimization of sensitivity and interpretability in nipt anomaly detection
Clinical machine learning faces a critical dilemma in high-stakes medical applications: algorithms achieving optimal diagnostic performance typically sacrifice the interpretability essential for physician decision-making…
Anomaly DetectionInvestigating Neuron Ablation in Attention Heads: The Case for Peak Activation Centering
The use of transformer-based models is growing rapidly throughout society. With this growth, it is important to understand how they work, and in particular, how the attention mechanisms represent concepts. Though there a…
DARTS-GT: Differentiable Architecture Search for Graph Transformers with Quantifiable Instance-Specific Interpretability Analysis
Graph Transformers (GTs) have emerged as powerful architectures for graph-structured data, yet remain constrained by rigid designs and lack quantifiable interpretability. Current state-of-the-art GTs commit to fixed GNN …
Transformer Circuit Faithfulness Metrics are not Robust
Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain beh…