Papers by Julie Shah
The Solvability of Interpretability Evaluation Metrics (2023.findings-eacl)
Copied to clipboard
| Challenge: | Feature attribution methods are often evaluated on metrics such as comprehensiveness and sufficiency. |
| Approach: | They propose to use beam search to define problem of optimizing an explanation for a metric . they also propose to evaluate the metric on one or more metrics to determine its solvability . |
| Outcome: | The proposed explainer can solve the problem of optimizing an explanation for a metric by beam search. |
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that models encode syntactic information redundantly . this allows researchers to boost models' performance by injecting syntaktic information into embeddings . |
| Approach: | They propose a new probe design that guides probes to consider all syntactic information present in embeddings. |
| Outcome: | The proposed model improves performance by injecting syntactic information into models. |
ExSum: From Local Explanations to Model Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | Interpretability methods are developed to understand the working mechanisms of black-box models. |
| Approach: | They propose a mathematical framework for quantifying model understanding with an explanation summary. |
| Outcome: | The proposed framework highlights limitations in the current practice and reveals easily overlooked properties of the model. |