mlsanityData to 14 Oct 2026

AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving

arXiv 2412.15206 ↗First posted 19 Dec 2024cs.CV cs.LG cs.ROcited by 35

On the map: LLM reasoning → Chain-of-thought reasoning for driving

also in 2 more
Abstract (arXiv)

Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeniable candidates for end-to-end driving systems. However, limited work exists on studying the trustworthiness of DriveVLMs -- a critical factor that directly impacts public transportation safety. In this paper, we introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs), considering diverse perspectives -- including trustfulness, safety, robustness, privacy, and fairness. We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios, comprising over 10k unique scenes and 18k queries. We evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models. Our exhaustive evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats. Specifically, we found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness. DriveVLMs like DriveLM-Agent are particularly vulnerable to disclosing sensitive information. Additionally, both generalist and specialist VLMs remain susceptible to adversarial attacks and struggle to ensure unbiased decision-making across diverse environments and populations. Our findings call for immediate and decisive action to address the trustworthiness of DriveVLMs -- an issue of critical importance to public safety and the welfare of all citizens relying on autonomous transportation systems. We release all the codes and datasets in https://github.com/taco-group/AutoTrust.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 52 of its 125 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

52 of 125 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning2 May
  2. 2023Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving6 Dec

Other references · 50

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  10. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  11. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  12. 2024Qwen2 Technical Reportcited by 2,120
38 more
  1. 2016Adversarial examples in the physical worldcited by 1,769
  2. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  3. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  4. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  5. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  6. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 584
  7. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  8. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 565
  9. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  10. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  11. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 231
  12. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  13. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  14. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 198
  15. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 167
  16. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 156
  17. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 145
  18. 2023Dolphins: Multimodal Language Model for Drivingcited by 124
  19. 2024Dissecting Adversarial Robustness of Multimodal LM Agentscited by 120
  20. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 92
  21. 2024CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Drivingcited by 77
  22. 2024Enhancing Large Vision Language Models with Self-Training on Image Comprehensioncited by 70
  23. 2024Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Charactercited by 68
  24. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 64
  25. 2024Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Reviewcited by 53
  26. 2024Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Drivingcited by 52
  27. 2024Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignmentcited by 42
  28. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priorscited by 36
  29. 2024Safety Alignment for Vision Language Modelscited by 28
  30. 2024Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Modelscited by 23
  31. 2024MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agentscited by 21
  32. 2020Self-Driving like a Human driver instead of a Robocar: Personalized comfortable driving experience for autonomous vehiclescited by 20
  33. 2023Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networkscited by 17
  34. 2024Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Modelscited by 13
  35. 2024Privacy-Aware Visual Language Modelscited by 12
  36. 2024The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Modelscited by 8
  37. 2024TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questionscited by 7
  38. 2022Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directionscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 10.

35 papers.

Sort:

By area:

  1. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
  2. 2025NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Drivingcited by 35
  3. 2025Can Large Vision Language Models Read Maps Like a Human?cited by 30
  4. 2025Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationcited by 29
  5. 2025UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Drivingcited by 28
  6. 2025LangCoop: Collaborative Driving with Languagecited by 25
  7. 2025SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systemscited by 25
  8. 2025DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learningcited by 24
  9. 2025Embodied Scene Understanding for Vision Language Models via MetaVQAcited by 19
  10. 2025DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learningcited by 16
  11. 2025CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perceptioncited by 13
  12. 2025Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospectscited by 12
23 more
  1. 2025JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Modelcited by 10
  2. 2025Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competitioncited by 9
  3. 2025Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Drivingcited by 8
  4. 2025Generative AI for Autonomous Driving: Frontiers and Opportunitiescited by 7
  5. 2025Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenescited by 7
  6. 2025DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Drivingcited by 5
  7. 2025Automated Vehicles Should be Connected with Natural Languagecited by 5
  8. 2025Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Drivingcited by 4
  9. 2025Demystifying the Visual Quality Paradox in Multimodal Large Language Modelscited by 3
  10. 2025Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidancecited by 3
  11. 2026ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Drivingcited by 3
  12. 2025SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Drivingcited by 2
  13. 2026Understanding Real-World Traffic Safety through RoadSafe365 Benchmarkcited by 2
  14. 2025HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debatecited by 1
  15. 2026Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAscited by 1
  16. 2025NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networkscited by 0
  17. 2026From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?cited by 0
  18. 2026NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Drivingcited by 0
  19. 2026From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Drivingcited by 0
  20. 2026Development of Vision-Language Model-based GNSS Spoofing Detection for Autonomous Vehicle Navigationcited by 0
  21. 2026Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenescited by 0
  22. 2026ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancementcited by 0
  23. 2026A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platformcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
  2. 2025Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
  3. 2025Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
  4. 2025A Survey on Vision-Language-Action Models for Autonomous Driving
  5. 2026Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models
  6. 2025Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving
  7. 2026Towards Reliable Vision-Language Models for Autonomous Driving
  8. 2025Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding