Characterize REALLY-KNOW Specifications as Causal Graphs
Fully characterize the validity and applicability of REALLY-KNOW specifications as causal graphs for estimating concept-level causal effects in vision-language models.
References
Nonetheless, further research is required to fully characterise the use of REALLY-KNOWs as causal graphs.
— DiaVLo: Diagnosing Behaviours of Vision-Language Models
(2609.22008 - Corti et al., 18 Sep 2026) in Section 5, “Results & Discussion,” subsection “REALLY-KNOWs as Causal Graphs”