# CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs

arXiv: https://arxiv.org/abs/2604.20460 · HTML: https://mlsanity.com/paper/2604.20460/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 27 of 27)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario](https://mlsanity.com/paper/2305.14836/) (2023)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [TVQA+: Spatio-Temporal Grounding for Video Question Answering](https://mlsanity.com/paper/1904.11574/) (2019)
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023)
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023)
- [Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives](https://mlsanity.com/paper/2501.04003/) (2025)
- [Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision](https://mlsanity.com/paper/2311.07362/) (2023)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer](https://mlsanity.com/paper/2407.17140/) (2024)
- [VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models](https://mlsanity.com/paper/2406.16338/) (2024)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding](https://mlsanity.com/paper/2412.03735/) (2024)
- [What is More Likely to Happen Next? Video-and-Language Future Event Prediction](https://mlsanity.com/paper/2010.07999/) (2020)
- [DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark](https://mlsanity.com/paper/1904.12634/) (2019)
- [EventHallusion: Diagnosing Event Hallucinations in Video LLMs](https://mlsanity.com/paper/2409.16597/) (2024)
- [VIOLIN: A Large-Scale Dataset for Video-and-Language Inference](https://mlsanity.com/paper/2003.11618/) (2020)
- [VidHal: Benchmarking Temporal Hallucinations in Vision LLMs](https://mlsanity.com/paper/2411.16771/) (2024)
- [STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving](https://mlsanity.com/paper/2506.06218/) (2025)
- [Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness](https://mlsanity.com/paper/2407.01942/) (2024)
- [EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding](https://mlsanity.com/paper/2508.12687/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mitigating Video Hallucinations via Attention-Guided Representation Perturbation](https://mlsanity.com/paper/2610.19728/) (2026)

## Abstract (arXiv)

Safety-critical traffic reasoning requires contrastive consistency: models must detect true hazards when an accident occurs, and reliably reject plausible-but-false hypotheses under near-identical counterfactual scenes. We present CCTVBench, a Contrastive Consistency Traffic VideoQA Benchmark built on paired real accident videos and world-model-generated counterfactual counterparts, together with minimally different, mutually exclusive hypothesis questions. CCTVBench enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, and mutual-exclusivity violation, while separating video versus question consistency. Experiments across open-source and proprietary video LLMs reveal a large and persistent gap between standard per-instance QA metrics and quadruple-level contrastive consistency, with unreliable none-of-the-above rejection as a key bottleneck. Finally, we introduce C-TCD, a contrastive decoding approach leveraging a semantically exclusive counterpart video as the contrast input at inference time, improving both instance-level QA and contrastive consistency.