Sean Xie
4 papers · 2023–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(2)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π§
Keyword Pioneer
π
Cross-Pollinator
(13)
Conferences
EMNLP (2)
NAACL (2)
Top co-authors
Research topics
Keywords
prototypical network
(2)
embedding learning
(1)
bias detection
(1)
case-based reasoning
(1)
language model
(1)
debiasing method
(1)
downstream task
(1)
healthcare application
(1)
pretrained language model
(1)
faithful explanation
(1)
axiomatic approach
(1)
white-box model
(1)
interpretable embedding
(1)
large language model
(1)
social bias mitigation
(1)
attention explanation
(1)
transfer learning
(1)
interpretability criterion
(1)
Papers
Bridging the Faithfulness Gap in Prototypical Models
NAACL 2025
IvRA: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training
EMNLP 2024
Addressing Healthcare-related Racial and LGBTQ+ Biases in Pretrained Language Models
NAACL 2024
Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models
EMNLP 2023