Amanda AskellResearch Scientist (Alignment Finetuning) · AnthropicResearcher↗
Researcher
Neil Rathi
AnthropicResearcher
Rathi studies whether language models communicate uncertainty in ways people can interpret and trust. His work shows that overconfident answers can cause users across languages to rely on wrong information, and explores how training-data controls can remove unwanted capabilities before deployment.
Career & education
Current role
Researcher
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations151As of Oct 5, '26
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 10, 2026 · Checked for accuracy and new information.
