Get started
Author

Asa Cooper Stickland

Observed names: Cooper Stickland, Asa, Stickland, Asa Cooper
OpenAlex ID: A5024678824
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
2019 · Stickland, Asa Cooper, Murray, Iain · arXiv (Cornell University) · 138
PDF
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
2019 · Cooper Stickland, Asa, Murray, Iain; id_orcid 0000-0002-6506-0472 · Edinburgh Research Explorer (University of Edinburgh) · 96
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
2023 · Berglund, Lukas, Tong, Meg, et al. · arXiv (Cornell University) · 36
PDF
Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
2021 · Asa Cooper Stickland, Xian Li, et al. · 32
PDF
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
2023 · Rein, David, Hou, Betty Li, et al. · arXiv (Cornell University) · 30
PDF
Deep Transformers with Latent Depth
2020 · Li, Xian, Stickland, Asa Cooper, et al. · arXiv (Cornell University) · 22
PDF
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
2021 · Stickland, Asa Cooper, Bérard, Alexandre, et al. · arXiv (Cornell University) · 15
PDF
Diverse Ensembles Improve Calibration
2020 · Stickland, Asa Cooper, Murray, Iain · arXiv (Cornell University) · 13
PDF
Taken out of context: On measuring situational awareness in LLMs
2023 · Berglund, Lukas, Stickland, Asa Cooper, et al. · arXiv (Cornell University) · 8
PDF
Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining
2023 · Asa Cooper Stickland, Sailik Sengupta, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 8
PDF
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
2024 · Sheshadri, Abhay, Ewart, Aidan, et al. · arXiv (Cornell University) · 3
PDF
When does Parameter-Efficient Transfer Learning Work for Machine Translation?
2022 · Ahmet Üstün, Asa Cooper Stickland · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 3
PDF
Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
2024 · Price, Sara, Panickssery, Arjun, et al. · arXiv (Cornell University) · 2
PDF
Steering Without Side Effects: Improving Post-Deployment Control of Language Models
2024 · Stickland, Asa Cooper, Lyzhov, Alexander, et al. · arXiv (Cornell University) · 1
PDF
Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings
2026 · Duzan, Agatha, Stickland, Asa Cooper · arXiv (Cornell University)
PDF
Distributed Attacks in Persistent-State AI Control
2026 · Hills, Josh, Caspary, Ida, et al. · arXiv (Cornell University)
PDF
Forecasting Future Behavior as a Learning Task
2026 · Levy, Mosh, Goldberg, Yoav, et al. · arXiv (Cornell University)
PDF
Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
2025 · Stickland, Asa Cooper, Michelfeit, Jan, et al. · arXiv (Cornell University)
PDF
Why Do Language Model Agents Whistleblow?
2025 · Agrawal, Kushal, Xiao, Frank, et al. · arXiv (Cornell University)
PDF
RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents
2025 · Black, Sid, Stickland, Asa Cooper, et al. · arXiv (Cornell University)
PDF
Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
2024 · Doshi, Jai, Stickland, Asa Cooper · arXiv (Cornell University)
PDF
Regularising Fisher Information Improves Cross-lingual Generalisation
2021 · Asa Cooper Stickland, Iain Murray · Workshop on Multilingual Representation Learning (MRL)
PDF
Works count: 23
Citation count: 407
H-index: 8
I10-index: 8
Year
Topic
Type