raid icon indicating copy to clipboard operation
raid copied to clipboard

LLM-Detector - test submission

Open Michal1337 opened this issue 4 months ago • 2 comments

Michal1337 avatar Sep 27 '25 14:09 Michal1337

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

LLM-detector

Release date: 2025-09-27

I've committed detailed results of this detector's performance on the test set to this PR.

On the RAID dataset as a whole (aggregated across all generation models, domains, decoding strategies, repetition penalties, and adversarial attacks), it achieved an AUROC of 89.26 and a TPR of 70.06% at FPR=5% and 59.94% at FPR=1%. Without adversarial attacks, it achieved AUROC of 95.83 and a TPR of 85.32% at FPR=5% and 77.19% at FPR=1%.

If all looks well, a maintainer will come by soon to merge this PR and your entry/entries will appear on the leaderboard. If you need to make any changes, feel free to push new commits to this PR. Thanks for submitting to RAID!

github-actions[bot] avatar Sep 27 '25 17:09 github-actions[bot]

@Michal1337 let me know if you'd like us to merge your submission!

liamdugan avatar Sep 28 '25 22:09 liamdugan