Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models

• URL: http://arxiv.org/abs/2605.17268v2
• Date: Sun, 24 May 2026 13:03:27 GMT
• Title: Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models
• Abstract summary: We analyze 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios.<n>Overall reasoning fidelity is only 42.5%, with Chain-of-Causation matching scene reality less than half the time.<n>We formalize faithfulness information-theoretically, define entity and action fidelity with verification criteria, and outline a four-component safety architecture aligned with these results.
• Score: 13.085985443741412
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language rationales with trajectories may be significantly unfaithful: (i) overall reasoning fidelity is only 42.5%, with Chain-of-Causation matching scene reality less than half the time; (ii) 94 missed pedestrians in one-third of pedestrian-relevant scenes; (iii) 97.7% trajectory fragility under mild visual perturbations; and (iv) only 48.3% mean reasoning-action consistency, with 53.3% of inferences exhibiting low consistency, including 37.9% of stop-claimed cases where the model continues instead. We formalize faithfulness information-theoretically, define entity and action fidelity with verification criteria, and outline a four-component safety architecture aligned with these results.

Related papers

• Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective [76.02772556944073]
  Environmental illusions are naturally existing yet overlooked phenomena in real-world driving environments.<n>They can disturb visual perception, leading to misinterpretation of the scene and posing serious safety risks to autonomous driving systems.<n>We introduce the first benchmark, LanEvil++, for evaluating the robustness of lane perception under environmental illusions.
  arXiv  Detail & Related papers  (2026-07-07T03:15:00Z)
• Evaluation Awareness Is Not One Capability: Evidence from Open Language Models [1.758143872501506]
  Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt.<n>This opens a gap between benchmark performance and deployment behavior.<n>We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families.
  arXiv  Detail & Related papers  (2026-06-22T16:48:43Z)
• Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models [3.7184769644515896]
  We present the first large-scale empirical mapping of AI decision-making across all three layers of the Authority Stack framework.<n>We evaluated 8 major AI models at temperature 0, yielding 366,120 total responses.
  arXiv  Detail & Related papers  (2026-04-13T09:13:32Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? [0.0]
  Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments.<n>This study tests 12 open-weight reasoning models spanning 9 architectural families on 498 multiple-choice questions.<n>Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families.
  arXiv  Detail & Related papers  (2026-03-23T21:21:37Z)
• AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning [14.20669481486209]
  We present a winning three-stage system for SemEval 2026 Task12: Abductive Event Reasoning.<n>Our system ranks first on the evaluation-phase leaderboard with an accuracy score of 0.95.
  arXiv  Detail & Related papers  (2026-03-04T17:38:52Z)
• When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models [54.08784776767683]
  We present Physical-Conditioned World Model Attack (PhysCond-WMA), the first white-box world model attack that perturbs physical-condition channels.<n>PhysCond-WMA induces semantic, logic, or decision-level distortion while preserving perceptual fidelity.
  arXiv  Detail & Related papers  (2026-02-21T07:22:37Z)
• CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks [53.88194225946438]
  Chain-of-Thought for Detection (CoT4Det) is a simple but efficient strategy that reformulates perception tasks into three interpretable steps.<n>We show that CoT4Det significantly improves perception performance without compromising general vision language capabilities.
  arXiv  Detail & Related papers  (2025-12-07T05:26:30Z)
• Beyond Mimicry: Preference Coherence in LLMs [0.19116784879310025]
  We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs.<n>We find 23 combinations (47.9%) demonstrated statistically significant relationships between scenario intensity and choice patterns.<n>Only 5 combinations (10.4%) demonstrate meaningful preference coherence through adaptive or threshold-based behavior.<n>The prevalence of unstable transitions (45.8%) and stimulus-specific sensitivities suggests current AI systems lack unified preference structures.
  arXiv  Detail & Related papers  (2025-11-17T17:41:48Z)
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail [85.47497935739936]
  Alpamayo-R1 (AR1) is a vision-language-action model that integrates Chain of Causation reasoning with trajectory planning.<n>We show AR1 achieves 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline.<n>We plan to release AR1 models and a subset of the CoC in a future update.
  arXiv  Detail & Related papers  (2025-10-30T01:25:34Z)
• SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection [6.806105013817923]
  SAVANT is a structured reasoning framework that achieves high accuracy and recall in detecting anomalous driving scenarios.<n>By automatically labeling over 9,640 real-world images with high accuracy, SAVANT addresses the critical data scarcity problem in anomaly detection.
  arXiv  Detail & Related papers  (2025-10-20T19:14:29Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense [61.78357530675446]
  Humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors.<n>Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation.<n>For an adversarial example, we aim to discriminate perturbations as non-causative factors and make predictions only based on the label-causative factors.
  arXiv  Detail & Related papers  (2024-10-30T15:06:44Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.