Sotabase

Career

· Research Assistant, Vector Institute2023–

Publications (31)

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
Neural Information Processing Systems · 2022
1,197
cited
BLiMP: The Benchmark of Linguistic Minimal Pairs for English
Transactions of the Association for Computational Linguistics · 2019
632
cited
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
Annual Meeting of the Association for Computational Linguistics · 2020
205
cited
The Semantic Scholar Open Data Platform
arXiv.org · 2023
145
cited
Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs
Conference on Empirical Methods in Natural Language Processing · 2019
128
cited
jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
Annual Meeting of the Association for Computational Linguistics · 2020
96
cited
Soft Merging of Experts with Adaptive Routing
Trans. Mach. Learn. Res. · 2023
82
cited
English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too
AACL · 2020
67
cited
Learning to Route Among Specialized Experts for Zero-Shot Generalization
International Conference on Machine Learning · 2024
57
cited
Comparing Test Sets with Item Response Theory
Annual Meeting of the Association for Computational Linguistics · 2021
52
cited
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
First Workshop on Insights from Negative Results in NLP · 2020
39
cited
Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · 2021
37
cited
LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks
arXiv.org · 2023
31
cited
Learning Helpful Inductive Biases from Self-Supervised Pretraining
Conference on Empirical Methods in Natural Language Processing · 2020
26
cited
BLiMP: A Benchmark of Linguistic Minimal Pairs for English
SCIL · 2020
15
cited
Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models
International Conference on Machine Learning · 2023
15
cited
Precise Task Formalization Matters in Winograd Schema Evaluations
Conference on Empirical Methods in Natural Language Processing · 2020
12
cited
Models with Conditional Computation Learn Suboptimal Solutions
2022
6
cited
Erratum: “BLiMP: The Benchmark of Linguistic Minimal Pairs for English”
Transactions of the Association for Computational Linguistics · 2020
5
cited
MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation
International Conference on Computational Linguistics · 2018
4
cited
Sotabase
Haokun Liu | Researcher Profile | Sotabase | Sotabase