Hillary Dawkins
10 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(24)
πΊ
Lone Wolf
(4)
π
Century Club
(10)
Conferences
ACL (5)
EMNLP (2)
IJCNLP (2)
COLING (1)
Top co-authors
Keywords
coreference resolution
(3)
large language model
(3)
gender bia
(2)
latent bia
(2)
natural language generation
(1)
named entity recognition
(1)
embedding space
(1)
ai safety
(1)
natural language inference
(1)
speaker recognition
(1)
class imbalance
(1)
safety alignment
(1)
token classification
(1)
model alignment
(1)
pre-trained language model
(1)
model safety
(1)
bias analysis
(1)
fine-tuned llm
(1)
ai-generated text detection
(1)
safety evaluation
(1)
Papers
When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
ACL 2025
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
ACL 2025
Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse
EMNLP 2024
WMT24 Test Suite: Gender Resolution in Speaker-Listener Dialogue Roles
EMNLP 2024
Projective Methods for Mitigating Gender Bias in Pre-trained Language Models
COLING 2024
Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classification
ACL 2022
Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution
IJCNLP 2021
Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution
ACL 2021
Marked Attribute Bias in Natural Language Inference
IJCNLP 2021
Marked Attribute Bias in Natural Language Inference
ACL 2021