Matthew Finlayson
7 papers · 2021–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
EMNLP (3)
ICLR (2)
ACL (1)
IJCNLP (1)
Top co-authors
Keywords
causal mediation analysis
(2)
subject-verb agreement
(2)
neural network
(2)
in-context learning
(1)
question answering
(1)
neural network interpretability
(1)
out-of-distribution generalization
(1)
benchmark dataset
(1)
language model
(1)
instruction learning
(1)
pre-trained language model
(1)
transformer fine-tuning
(1)
pretrained language model
(1)
regular expression
(1)
syntactic structure
(1)
out-of-distribution performance
(1)
multiple-choice question
(1)
probability mass
(1)
t5 model
(1)
transformer model
(1)
Papers
Closing the Curious Case of Neural Text Degeneration
ICLR 2024
Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy
EMNLP 2023
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
ICLR 2023
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
EMNLP 2022
LILA: A Unified Benchmark for Mathematical Reasoning
EMNLP 2022
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
ACL 2021
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
IJCNLP 2021