most citedFool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models

Bayar Menzat, Maximilian Süss, Ruizhi Wang +3

Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the faithfulness of CoTs for tex…