LABEL
A paper that studies the asymmetry between drug indications and contraindications as recorded in publicly available text, and examines whether language models inherit this bias.
Timeline (last 90 days)
A study named LABEL analyzed how 574 drugs are described in Wikipedia and PubMed abstracts, finding that public text records contraindications far less than indications.
In Wikipedia articles and PubMed abstracts, drug benefits are mentioned about twice as often as safety restrictions, with a within-drug odds ratio of 2.19.
When the researchers provided the model with a retrieved passage that explicitly stated the answer, the model's utilization efficiency of safety facts was comparable to that of benefit facts.
The root cause of the model's failures on drug safety lies in the scarcity of safety facts in free-text corpora, not in defects in the model's reasoning ability.
The research team has released the code and data of the LABEL study for subsequent research to reproduce and extend.
All Facts (5)
A study named LABEL analyzed how 574 drugs are described in Wikipedia and PubMed abstracts, finding that public text records contraindications far less than indications.
50%UnverifiedIn Wikipedia articles and PubMed abstracts, drug benefits are mentioned about twice as often as safety restrictions, with a within-drug odds ratio of 2.19.
50%UnverifiedWhen the researchers provided the model with a retrieved passage that explicitly stated the answer, the model's utilization efficiency of safety facts was comparable to that of benefit facts.
50%UnverifiedThe root cause of the model's failures on drug safety lies in the scarcity of safety facts in free-text corpora, not in defects in the model's reasoning ability.
50%UnverifiedThe research team has released the code and data of the LABEL study for subsequent research to reproduce and extend.
50%