Get started
Author

Urja Pawar

Observed name: Pawar, Urja
Institution: Brooklyn Navy Yard
Observed institution: Brooklyn Navy Yard
OpenAlex ID: A5126518984
Full experimental record for "Strangers to Themselves" paper
2026 · Blandfort, Phil, Pawar, Urja · Zenodo (CERN European Organization for Nuclear Research)
Strangers to Themselves: What Language Models Say About Themselves Is Generic
2026 · Blandfort, Phil, Pawar, Urja · arXiv (Cornell University)
PDF
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence
2026 · Pawar, Urja, Ramanayake, Rajitha, et al. · arXiv (Cornell University)
PDF
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
2026 · Pawar, Urja, Ramanayake, Rajitha, et al. · arXiv (Cornell University)
PDF
Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs
2026 · Blandfort, Phil, Karayil, Tushar, et al. · arXiv (Cornell University)
PDF
Result Files for "Moral Preferences under Directed Contextual Influences"
2026 · Blandfort, Philipp, Karayil, Tushar, et al. · Zenodo (CERN European Organization for Nuclear Research)
Detecting High-Stakes Interactions with Activation Probes
2025 · Alex McKenzie, Urja Pawar, et al. · neural information processing systems
PDF
Works count: 7
Citation count:
H-index:
I10-index:
Year
Topic
Type