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

2026-09-06

AI Summary

本文针对视觉语言模型中思维链的忠实度测量问题，通过适应反事实测试方法（vCT和vCCT）来评估八个开源视觉语言模型，揭示了思维链与视觉证据之间的不一致性。

Abstract

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 textual inputs have been increasingly introduced, using these methods for visual inputs is not straightforward. In this work, we adapt the family of counterfactual methods for measuring CoT faithfulness, namely the Counterfactual Test (CT) and Correlational Counterfactual Test (CCT), to visual inputs, and call them vCT and vCCT, respectively. Using vCT and vCCT, we benchmark eight recent open-source Vision Language Models (VLMs) on two datasets. Our analysis shows that CoTs do not reliably track visual evidence that influences model predictions: they may omit the removed object even when its removal causes a large prediction shift, yet mention it when the shift is small. We further find that Predict-then-Explain explanations align more strongly with perturbation-induced probability shifts than pre-answer CoTs, while binary vCT scores are often nearly saturated. We also include a reconstruction control, in which images pass through the same editing pipeline without object removal, and find that the main object-removal intervention induces larger shifts than reconstruction alone. We construct and release Counter-SNLI-VE and Counter-A-OKVQA, two datasets of image pairs that differ by a single object.

Problem

• Chain-of-Thought
• Visual Language Models
• Faithfulness
• Counterfactual Tests

Innovation

• Counterfactual Test
• Visual Language Models
• Chain-of-Thought Faithfulness