ImplicIT-Mis
A dataset for evaluating implicit misogyny detection, potentially containing English and Italian samples, focused on testing a model's ability to identify implicit gender discrimination.
Timeline (last 90 days)
The study uses two datasets, ImplicIT-Mis and SBIC+, to evaluate the contribution of each knowledge source to detection and explanation quality.
On the ImplicIT-Mis dataset, RAG improved recall, meaning the model was able to capture more previously missed implicit misogyny cases.
ImplicIT-Mis is a dataset built specifically for implicit misogyny, covering English and Italian, whose samples often lack explicit cues and require background knowledge to judge.
All Facts (3)
The study uses two datasets, ImplicIT-Mis and SBIC+, to evaluate the contribution of each knowledge source to detection and explanation quality.
50%UnverifiedOn the ImplicIT-Mis dataset, RAG improved recall, meaning the model was able to capture more previously missed implicit misogyny cases.
50%UnverifiedImplicIT-Mis is a dataset built specifically for implicit misogyny, covering English and Italian, whose samples often lack explicit cues and require background knowledge to judge.
50%