◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Urja Pawar

2 papers hereh-index 5514 citations14 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author2

Across the 2 of 2 papers where every author was matched, so the position is known.

fields
  • cs.LG2

identity via Semantic Scholar / OpenAlex

collaborators

2 papers

cs.LG2026

Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs

Phil Blandfort, Tushar Karayil, Alex McKenzie +3

Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this assumption with a direction-flipped i…

cs.LG2026

Detecting High-Stakes Interactions with Activation Probes

Alex McKenzie, Urja Pawar, Phil Blandfort +4

Monitoring is an important aspect of safely deploying Large Language Models (LLMs). This paper examines activation probes for detecting ``high-stakes'' interactions -- where the te…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.