Get started
Author

David Williams-King

Observed name: Williams-King, David
OpenAlex ID: A5120001465
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
2026 · Le, Linh, Bui, Melanie, et al. · arXiv (Cornell University)
PDF
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
2026 · Le, Linh, Tan, Hong Kiat, et al. · arXiv (Cornell University)
PDF
A Causal Model for Locating and Unlocking Sandbagging in Model Organisms
2026 · Tan, Hong Kiat, Le, Linh, et al. · arXiv (Cornell University)
PDF
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026 · Merzouk, Mohamed Amine, Smyth, Nolan, et al. · arXiv (Cornell University)
PDF
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
2026 · Khoriaty, Matthew, Williams-King, David, et al. · arXiv (Cornell University)
PDF
Behavioural Analysis of Alignment Faking
2026 · Hadida, Nathaniel Mitrani, Karty, Rhea, et al. · arXiv (Cornell University)
PDF
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
2026 · Mehta, Astha, Selvanayagam, Niruthiha, et al. · arXiv (Cornell University)
PDF
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
2026 · Le, Linh, Williams-King, David, et al. · arXiv (Cornell University)
PDF
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
2026 · Wachowiak, Lennart, Blain, Scott D., et al. · arXiv (Cornell University)
PDF
Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning
2026 · Luong, Isabella, Chen, Joyee, et al. · arXiv (Cornell University)
PDF
Representation Engineering for Large-Language Models: Survey and Research Challenges
2025 · Bartoszcze, Lukasz, Munshi, Sarthak, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count:
H-index:
I10-index:
Year
Topic
Type