Skip to content

Contrib population span extraction #1087

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

Contrib population span extraction #1087

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c921635
contributing a custom eval to the repository. The model is tasked to …
IGES-Institut Jun 2, 2023
b0d6c2e
Made sure to move the JSON file to Git LFS before submitting a PR
IGES-Institut Jun 2, 2023
f895999
reverted changes to .gitattribute
IGES-Institut Jun 7, 2023
a75f6b6
added a proper description for the eval in the .yaml file
IGES-Institut Jun 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .gitattributes
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
evals/registry/data/**/*.jsonl filter=lfs diff=lfs merge=lfs -text
evals/registry/data/**/*.jsonl filter=lfs diff=lfs merge=lfs -text
3 changes: 3 additions & 0 deletions evals/registry/data/population_span_extraction/samples.jsonl
View file
Open in desktop
Git LFS file not shown
13 changes: 13 additions & 0 deletions evals/registry/evals/population_span_extraction.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
# Register the eval by adding a file to evals/registry/evals/<eval_name>.yaml
population_span_extraction:
id: population_span_extraction.dev.v0
metrics: [accuracy]
description: The model is shown abstracts of clinical drug trials and tasked with extracting the text spans that specify the population demographic of the shown abstract. The population demographic can be but is not necessarily specified in multiple seperate spans.

population_span_extraction.dev.v0:
# Assuming that the response can contain "significant variation" --> modelbased classify
class: evals.elsuite.modelgraded.classify:ModelBasedClassify
args:
samples_jsonl: population_span_extraction/samples.jsonl
eval_type: cot_classify
modelgraded_spec: fact