Marcos André Gonçalves
5 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(13)
Conferences
ACL (2)
EMNLP (2)
CONLL (1)
Top co-authors
Keywords
contextual embedding
(2)
large language model
(2)
error analysis
(2)
text classification
(2)
class imbalance
(1)
support vector machine
(1)
language model
(1)
bias reduction
(1)
random forest
(1)
linguistic phenomenon
(1)
small language model
(1)
imbalanced dataset
(1)
classifier bia
(1)
irony detection
(1)
classifier interpretability
(1)
sentiment analysis
(1)
balanced brier score
(1)
sentiment classification
(1)
confidence calibration
(1)
computational efficiency
(1)
Papers
When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score
ACL 2026
Instance-Selection-Inspired Undersampling Strategies for Bias Reduction in Small and Large Language Models for Binary Text Classification
ACL 2025
Calibration as a Proxy for Fairness and Efficiency in a Perspectivist Ensemble Approach to Irony Detection
EMNLP 2025
Explaining the Hardest Errors of Contextual Embedding Based Classifiers
CONLL 2024
Explaining the Hardest Errors of Contextual Embedding Based Classifiers
EMNLP 2024