Add MedFailBench medical AI safety task#3918
Open
goktugozkanmd wants to merge 1 commit into
Open
Conversation
Adds a zero-shot generate-until task for MedFailBench using the public Hugging Face prompt dataset.\n\nValidation:\n- lm-eval validate --tasks medfailbench\n- lm-eval run --model dummy --model_args pretrained=dummy --tasks medfailbench --limit 1 Signed-off-by: Göktuğ Özkan, MD <232098340+goktugozkanmd@users.noreply.github.com>
6 tasks
Author
|
Revalidated this against current
The smoke run loaded the public Hugging Face dataset and completed successfully. The branch is current and has no open review threads. @baberabb @0xSMT, could one of you review when you have bandwidth? |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
medfailbenchtask for Medical AI Failure Atlas / MedFailBenchgoktugozkanmd/medfailbench-v02-promptsContext
This implements the task proposed in #3866.
MedFailBench is a clinician-authored medical AI safety benchmark focused on unsafe clinical response patterns, bilingual Turkish/English prompts, and downstream SafetyGuard scoring.
Validation
lm-eval validate --tasks medfailbenchlm-eval run --model dummy --model_args pretrained=dummy --tasks medfailbench --limit 1 --output_path /tmp/lm_eval_medfailbench_run