SABRE is a modular pipeline for automatically building and refreshing VLM stress tests, and its SABRE-Prior instantiation finds that six frontier VLMs score 17.8 to 31.3 percent when visual evidence conflicts with world priors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SABRE: Scalable and Automated Benchmarking of VLMs under Stress
SABRE is a modular pipeline for automatically building and refreshing VLM stress tests, and its SABRE-Prior instantiation finds that six frontier VLMs score 17.8 to 31.3 percent when visual evidence conflicts with world priors.