Carlos Aguirre
@carlosaguirre.bsky.social
Applied Scientist @ Amazon
(Posts are my own opinion)
Previously PhD@JHU
(Posts are my own opinion)
Previously PhD@JHU
“Transferring Fairness using Multi-Task Learning with Limited Demographic Information”
We show we’re able to transfer the fairness to a target task without demographics from a helper task with demographics! It also works for intersectional fairness!
aclanthology.org/2024.nlp4pi-...
We show we’re able to transfer the fairness to a target task without demographics from a helper task with demographics! It also works for intersectional fairness!
aclanthology.org/2024.nlp4pi-...
Transferring Fairness using Multi-Task Learning with Limited Demographic Information
Carlos Alejandro Aguirre, Mark Dredze. Proceedings of the Third Workshop on NLP for Positive Impact. 2024.
aclanthology.org
November 19, 2024 at 2:27 AM
“Transferring Fairness using Multi-Task Learning with Limited Demographic Information”
We show we’re able to transfer the fairness to a target task without demographics from a helper task with demographics! It also works for intersectional fairness!
aclanthology.org/2024.nlp4pi-...
We show we’re able to transfer the fairness to a target task without demographics from a helper task with demographics! It also works for intersectional fairness!
aclanthology.org/2024.nlp4pi-...
“Selecting Shots for Demographic Fairness in Few-Shot Learning with LLMs”
We evaluate different example selection methods (semantic- and demographic-based) finding that semantic similarity works best for fairness, but it’s not the best all the time!
aclanthology.org/2024.nlp4pi-...
We evaluate different example selection methods (semantic- and demographic-based) finding that semantic similarity works best for fairness, but it’s not the best all the time!
aclanthology.org/2024.nlp4pi-...
Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models
Carlos Alejandro Aguirre, Kuleen Sasse, Isabel Alyssa Cachola, Mark Dredze. Proceedings of the Third Workshop on NLP for Positive Impact. 2024.
aclanthology.org
November 19, 2024 at 2:27 AM
“Selecting Shots for Demographic Fairness in Few-Shot Learning with LLMs”
We evaluate different example selection methods (semantic- and demographic-based) finding that semantic similarity works best for fairness, but it’s not the best all the time!
aclanthology.org/2024.nlp4pi-...
We evaluate different example selection methods (semantic- and demographic-based) finding that semantic similarity works best for fairness, but it’s not the best all the time!
aclanthology.org/2024.nlp4pi-...