pith. sign in

Arya Shah

Identifiers

  • name variant Arya Shah 0.60 · backfill

Papers (5)

  1. Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models cs.CL · 2026 · author #1
  2. SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters cs.CV · 2026 · author #1
  3. Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation cs.CV · 2026 · author #1
  4. GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees cs.LG · 2026 · author #1
  5. Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models cs.CL · 2026 · author #1

Mentions

  • 2606.08451 #1 · arxiv_oai · confidence 0.70 Arya Shah

Frequent Coauthors