diff --git a/evals/registry/data/population_span_extraction/samples.jsonl b/evals/registry/data/population_span_extraction/samples.jsonl new file mode 100644 index 0000000000..5d63a3d894 --- /dev/null +++ b/evals/registry/data/population_span_extraction/samples.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dce5e57cb3fe18df839314fcc0047ae4db9cc97af6f7cdcfd81c23ec788c587 +size 1076022 diff --git a/evals/registry/evals/population_span_extraction.yaml b/evals/registry/evals/population_span_extraction.yaml new file mode 100644 index 0000000000..0e6cebf2eb --- /dev/null +++ b/evals/registry/evals/population_span_extraction.yaml @@ -0,0 +1,11 @@ +population_span_extraction: + id: population_span_extraction.dev.v0 + 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. + metrics: [accuracy] + +population_span_extraction.dev.v0: + class: evals.elsuite.modelgraded.classify:ModelBasedClassify + args: + samples_jsonl: population_span_extraction/samples.jsonl + eval_type: cot_classify + modelgraded_spec: fact \ No newline at end of file