Dylan Slack
8 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ฃ Hot Topic Early Bird ๐ Conference Polyglot (4) ๐ Cross-Pollinator (12)
๐บ๏ธ
Taxonomy Completionist
(16)
Conferences
NIPS (5)
ACL (1)
EMNLP (1)
IJCNLP (1)
Top co-authors
Keywords
large language model
(2)
representation learning
(1)
contrastive learning
(1)
benchmark evaluation
(1)
adversarial robustness
(1)
reward modeling
(1)
algorithmic fairness
(1)
transfer learning
(1)
mathematical reasoning
(1)
in-context learning
(1)
language modeling
(1)
privacy preservation
(1)
feature importance
(1)
model interpretability
(1)
reinforcement learning from human feedback
(1)
model uncertainty
(1)
bayesian framework
(1)
language model
(1)
foundation model
(1)
counterfactual explanation
(1)
Papers
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
NIPS 2024
Learning Goal-Conditioned Representations for Language Reward Models
NIPS 2024
Post Hoc Explanations of Language Models Can Improve Language Models
NIPS 2023
On the Lack of Robust Interpretability of Neural Text Classifiers
IJCNLP 2021
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
NIPS 2021
On the Lack of Robust Interpretability of Neural Text Classifiers
ACL 2021
Counterfactual Explanations Can Be Manipulated
NIPS 2021
Differentially Private Language Models Benefit from Public Pre-training
EMNLP 2020