Scholar
Nicholas Andrews
Google Scholar ID: O_7mcrMAAAAJ
Johns Hopkins University
Citations & Impact
Citations
953
H-index
13
i10-index
14
Publications
20
Co-authors
35
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Recent Work: Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback. This paper systematically investigates LLMs' ability to incorporate feedback by designing a controlled experimental environment. Even under near-ideal conditions, solver models consistently show resistance to feedback, a limitation termed FEEDBACK FRICTION. Several strategies were experimented with to mitigate this, but the models still failed to achieve target performance.
Research Experience
- He and his collaborators work on diverse problems, including detecting machine-generated content and anonymization.
Background
- He is a Senior Research Scientist at the Human Language Technologies Center of Excellence with a secondary appointment in the Department of Computer Science. His interests are broadly in generative AI, especially in how traditional tools from probability and statistics can be married with deep learning to create more capable AI systems and mitigate the associated risks. He is interested in various kinds of grounded language learning, most recently in the context of LLM agents. He's also interested in better understanding generative AI systems to mitigate potential abuses.
Miscellany
- Contact: noa@jhu.edu
- Address: 810 Wyman Park Drive, Baltimore, MD 21211
