Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning
Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models. However, whether this verbalized Chain-of-Thought truthfully reflects the policy's underlying decision process remains poorly understood. We distinguish between functional reasoning, in which reasoning improves task performance, and faithful reasoning, in which reasoning truly reflects the policy's internal decision process. We argue that SoTA alignment strategies offer a necessary but insufficient notion of faithfulness, admitti
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Alignment →
- PossiblePossibly related (embedding) · 46%sou350121/VLA-Handbook →
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “Do Vision-Language-Action Models Mean What They Say? On the ” ≈ “VioletVision-3B””
- LinkedLinked via arxiv author · 85%Matthew Foutter →
“Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning”
- LinkedLinked via arxiv author · 85%Matteo Cercola →
“Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning”
- LinkedLinked via arxiv author · 85%Lena Wild →
“Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning”
- LinkedLinked via arxiv author · 85%Yunshan Wang →
“Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning”
- LinkedLinked via arxiv author · 85%Michelle Li →
“Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning”