Research

Workshop papers

• Auditing Chain-of-Thought Faithfulness for Trustworthy AI: A Reproducible Corruption-Probe Protocol Across Eleven Frontier LLMs

  Saffarini, A., & Bagdasarian, A.

  Trustworthy AI for Good (AI4GOOD) Workshop, ICML, 2026

  Auditing Chain-of-Thought Faithfulness for Trustworthy AI: A Reproducible Corruption-Probe Protocol Across Eleven Frontier LLMs

Work under review

• Brokered Global Engagement Through Patronal Repurposing: Evolution and Structure of Russia’s Adaptation Networks.

  Hoppe, S., Filippova, A., & Bagdasarian, A.

  Under review.

  Brokered Global Engagement Through Patronal Repurposing: Evolution and Structure of Russia’s Adaptation Networks.

Work in progress

• Adapting psychometric test-equating to separate real social change from language-model version drift when a construct is tracked over time.

  Bagdasarian, A.

  (In progress.)

• Detecting coordinated and AI-generated comment campaigns in government rulemaking records at scale.

  Bagdasarian, A.

  (In progress.)