Mattia Samory
6 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
EMNLP (2)
NAACL (2)
ACL (1)
SEMEVAL (1)
Top co-authors
Keywords
model robustness
(2)
counterfactual augmentation
(2)
hate speech detection
(2)
information retrieval
(2)
cross-linguistic analysis
(2)
counterfactual data augmentation
(2)
semantic similarity
(2)
multilingual nlp
(2)
out-of-domain generalization
(2)
spurious feature
(2)
counterfactually augmented datum
(2)
annotator sensitivity
(1)
model bia
(1)
construct-driven perturbation
(1)
transformer model
(1)
social computing
(1)
multilingual news article
(1)
textual overlap
(1)
harmful language detection
(1)
news article similarity
(1)
Papers
Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness
ACL 2025
People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
EMNLP 2023
Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection
NAACL 2022
SemEval-2022 Task 8: Multilingual news article similarity
NAACL 2022
SemEval-2022 Task 8: Multilingual news article similarity
SEMEVAL 2022
How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
EMNLP 2021