Mark Díaz
11 papers · 2019–2024 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🧭 Keyword Pioneer 🐝 Cross-Pollinator (9) 🌍 Conference Polyglot (7) 🏃 Academic Marathon (5) 🌈 Renaissance Researcher (5)
🗺️
Taxonomy Completionist
(19)
🌍
Conference Polyglot
(7)
🏃
Academic Marathon
(5)
👥
Mega-Team
(67)
💎
Century Club
(11)
🗃️
Keyword Collector
(50)
⚡
Prolific Year
(5)
Conferences
EMNLP (3)
COLING (2)
NAACL (2)
ACL (1)
IJCAI (1)
JMLR (1)
NIPS (1)
Top co-authors
Keywords
ai safety
(3)
human annotation
(2)
safety evaluation
(2)
conversational ai
(2)
dataset bia
(1)
label aggregation
(1)
text classification
(1)
group fairness
(1)
offensive language detection
(1)
crowdsourced annotation
(1)
language model
(1)
social bia
(1)
red teaming
(1)
word embedding
(1)
bias mitigation
(1)
sentiment analysis
(1)
social norm
(1)
annotation disagreement
(1)
offensive language
(1)
few-shot learning
(1)
Papers
GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives
NAACL 2024
Intersectionality in AI Safety: Using Multilevel Models to Understand Diverse Perceptions of Safety in Conversational AI
COLING 2024
Diversity-Aware Annotation for Conversational AI Safety
COLING 2024
D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
EMNLP 2024
STAR: SocioTechnical Approach to Red Teaming Language Models
EMNLP 2024
DICES Dataset: Diversity in Conversational AI Evaluation for Safety
NIPS 2023
Relationality and Offensive Speech: A Research Agenda
ACL 2023
PaLM: Scaling Language Modeling with Pathways
JMLR 2023
Accounting for Offensive Speech as a Practice of Resistance
NAACL 2022
On Releasing Annotator-Level Labels and Information in Datasets
EMNLP 2021
Addressing Age-Related Bias in Sentiment Analysis
IJCAI 2019