POPQUORN
PulseAugur coverage of POPQUORN — every cluster mentioning POPQUORN across labs, papers, and developer communities, ranked by signal.
-
LLMs show demographic biases in text annotation, new study finds
A new research paper investigates the demographic biases inherent in large language models (LLMs) when they are used for text annotation. The study, conducted on the POPQUORN dataset, explores how LLMs mimic attributes …
-
Soft-label training enhances classifier accuracy by using full annotation distributions
Researchers have proposed a new training method called soft-label training for supervised classifiers, which utilizes the full distribution of annotator labels rather than a single majority vote. This approach is partic…
-
Research paper questions utility of demographic data in hate speech detection
A new research paper explores the effectiveness of using demographic information in hate speech detection models. The study found that demographic features are not universally beneficial and their utility depends on spe…