specificityplus
specificityplus copied to clipboard
👩💻 Code for the ACL paper "Detecting Edit Failures in LLMs: An Improved Specificity Benchmark"
Results
2
specificityplus issues
Sort by
recently updated
recently updated
newest added
https://github.com/jas-ho/memitpp/pull/47 adds barplots grouped by dataset. These plots are still missing errorbars. Asymmetric errorbars for pandas barplots turn out to be surprisingly tricky to get right; hence, the separate issue