Get started
Author

Oskar John Hollinsworth

Observed names: Hollinsworth, Oskar, Hollinsworth, Oskar J., Hollinsworth, Oskar John, Oskar J. Hollinsworth
ORCID: 0009-0007-0919-8593
Observed ORCID: 0009-0007-0919-8593
OpenAlex ID: A5114617734
Linear Representations of Sentiment in Large Language Models
2023 · Tigges, Curt, Hollinsworth, Oskar John, et al. · arXiv (Cornell University) · 8
PDF
Language Models Linearly Represent Sentiment
2024 · Oskar John Hollinsworth, Curt Tigges, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 7
PDF
Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
2026 · Hollinsworth, Oskar J., Spies, Alex F., et al. · arXiv (Cornell University)
PDF
Scaling Trends for Lie Detector Oversight in Preference Learning
2026 · Hollinsworth, Oskar J., Dombrowski, Ann-Kathrin, et al. · arXiv (Cornell University)
PDF
Bad influence: LLMs can transmit malicious traits using hidden signals
2026 · Oskar J. Hollinsworth, Samuel Bauer · Nature
STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Ian R. McKenzie, Oskar John Hollinsworth, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
1174 - STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Association for Artificial Intelligence 2026, Casper, Stephen, et al. · Underline Science Inc.
STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Association for Artificial Intelligence 2026, Casper, Stephen, et al. · Underline Science Inc.
STACK: Adversarial Attacks on LLM Safeguard Pipelines
2025 · McKenzie, Ian R., Hollinsworth, Oskar J., et al. · arXiv (Cornell University)
PDF
Scaling Trends in Language Model Robustness
2024 · Howe, Nikolaus, McKenzie, Ian, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 15
H-index: 2
I10-index:
Year
Topic
Type