mlsanityData to 14 Oct 2026

A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving

arXiv 2511.06496 ↗First posted 9 Nov 2025cs.RO cs.AI cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

also in 1 more
Abstract (arXiv)

Vision Language Models (VLMs) are increasingly used in autonomous driving to help understand traffic scenes, but they sometimes produce hallucinations, which are false details not grounded in the visual input. Detecting and mitigating hallucinations is challenging when ground-truth references are unavailable and model internals are inaccessible. This paper proposes a novel self-contained low-rank approach to automatically rank multiple candidate captions generated by multiple VLMs based on their hallucination levels, using only the captions themselves without requiring external references or model access. By constructing a sentence-embedding matrix and decomposing it into a low-rank consensus component and a sparse residual, we use the residual magnitude to rank captions: selecting the one with the smallest residual as the most hallucination-free. Experiments on the NuScenes dataset demonstrate that our approach achieves 87% selection accuracy in identifying hallucination-free captions, representing a 19% improvement over the unfiltered baseline and a 6-10% improvement over multi-agent debate method. The sorting produced by sparse error magnitudes shows strong correlation with human judgments of hallucinations, validating our scoring mechanism. Additionally, our method, which can be easily parallelized, reduces inference time by 51-67% compared to debate approaches, making it practical for real-time autonomous driving applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 25 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

20 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Hallucination of Multimodal Large Language Models: A Survey29 Apr

Other references · 19

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  8. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  9. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  10. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  11. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 262
  12. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 141
7 more
  1. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  2. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 99
  3. 2024CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Drivingcited by 77
  4. 2024Driving Everywhere with Large Language Model Policy Adaptationcited by 53
  5. 2024VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenescited by 23
  6. 2024Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debatecited by 16
  7. 2025Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Taskscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering
  2. 2024Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios
  3. 2024Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
  4. 2025Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
  5. 2026HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token
  6. 2025Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
  7. 2026One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs
  8. 2024Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding