AI answer engines cite sources based on relevance and position

A new research paper explores how AI answer engines decide which sources to cite, a crucial factor for visibility beyond simple ranking. The study found that topical relevance and list position are the most significant drivers for a source to be cited first. Factors like explicit price information and recent timestamps also positively influence citation likelihood, while completeness and trust cues offer smaller gains, and formatting changes have minimal impact. AI

IMPACT Provides a framework for optimizing source visibility in AI answer engines, impacting how content creators and search engines approach information surfacing.

RANK_REASON Academic paper detailing a new evaluation protocol for AI answer engines. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• AI answer engines
• Sprinklr

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →