Author

A. Pakrashi

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Review Sep 2026

Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks

Human-model alignment is critical for trustworthy AI-assisted decision-making systems. Yet, most work evaluates model predictions against single ground-truth labels, overlooking that humans themselves often disagree on labels, a signal of genuine ambiguity. We investigate whether models struggle on the same instances t...

Manya Singh, A. Pakrashi · 0 citations

Preprint Aug 2026

Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency

The Robust Ambiguity Detection (RAD) framework is advanced for quantifying predictive ambiguity using two complementary metrics: Model-Space Consistency and Feature-Space Consistency, which provide an interpretable characterisation of the sources of ambiguity and the actions a user may consider in response.

Manya Singh, Markt Keane, A. Pakrashi · 0 citations