Disinformation detectors trained mainly on Standard American English show systematic F1 drops on 50 English dialects, with multilingual models far more robust than monolingual ones.
arXiv preprint arXiv:2006.00885 (2020)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 3roles
dataset 1polarities
use dataset 1representative citing papers
CoALFake uses human-LLM co-annotation and domain-aware active learning to improve cross-domain fake news detection with low human effort.
PSS-TL uses dual independent teachers and multi-channel knowledge distillation to let a student model learn semantic and structural features without mutual interference for more robust fake news detection.
citing papers explorer
-
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects
Disinformation detectors trained mainly on Standard American English show systematic F1 drops on 50 English dialects, with multilingual models far more robust than monolingual ones.
-
CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection
CoALFake uses human-LLM co-annotation and domain-aware active learning to improve cross-domain fake news detection with low human effort.
-
Propagation Structure-Semantic Transfer Learning for Robust Fake News Detection
PSS-TL uses dual independent teachers and multi-channel knowledge distillation to let a student model learn semantic and structural features without mutual interference for more robust fake news detection.