One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques — mentioned by babel_

Fri, 29 Mar 2024 02:31:57 GMT

I think the situation with regulations will be similar to that with interpretability and explanations. There's a popular phrase that gets thrown around, that "there is no silver bullet" (perhaps most poignantly in AIX360's initial paper [0]), as no single explanation suffices (otherwise, would we not simply use that instead?) and no single static selection of them would either. What we need is to have flexible, adaptable approaches that can interactively meet the moment, likely backed by a large selection of well understood, diverse, and disparate approaches that cover for one other in a…

Paper and discussion history. A mention is not an endorsement.

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques · HackerPapers discussions

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques — mentioned by babel_