# What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs

arXiv: https://arxiv.org/abs/2606.01624 · HTML: https://mlsanity.com/paper/2606.01624/

## Key facts

- No citing papers in the map yet (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 41 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

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

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023)
- [DRAMA: Joint Risk Localization and Captioning in Driving](https://mlsanity.com/paper/2209.10767/) (2022)
- [RADIATE: A Radar Dataset for Automotive Perception in Bad Weather](https://mlsanity.com/paper/2010.09076/) (2020)
- [Canadian Adverse Driving Conditions Dataset](https://mlsanity.com/paper/2001.10117/) (2020)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving](https://mlsanity.com/paper/2305.02008/) (2023)
- [Automated Data Slicing for Model Validation:A Big data - AI Integration Approach](https://mlsanity.com/paper/1807.06068/) (2018)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model](https://mlsanity.com/paper/2412.09951/) (2024)
- [TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes](https://mlsanity.com/paper/2502.02449/) (2025)
- [ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones](https://mlsanity.com/paper/2406.07661/) (2024)
- [PeSOTIF: a Challenging Visual Dataset for Perception SOTIF Problems in Long-tail Traffic Scenarios](https://mlsanity.com/paper/2211.03402/) (2022)
- [ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models](https://mlsanity.com/paper/2409.00301/) (2024)
- [Coverage Metrics for a Scenario Database for the Scenario-Based Assessment of Automated Driving Systems](https://mlsanity.com/paper/2409.01139/) (2024)
- [AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis](https://mlsanity.com/paper/2212.09032/) (2022)

## Abstract (arXiv)

Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verification remains sparse: many slices are missing, making empirical failure rates unreliable. We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation that combines (i) an exposure-based coverage prior to prioritize rare, under-tested regions, and (ii) a neighbor-failure prior that propagates risk from similar tested conditions. SliceScorer is deliberately simple - interpretable, auditable, and conservative - properties essential for safety-critical validation. For stress testing beyond the declared ODD, we embed SliceScorer within SliceNav, an LLM-orchestrated verification pipeline where the model interprets developer queries to select relevant operators (triage, scoring, acquisition, evaluation) and vocabulary extensions, composing verification workflows while keeping all scoring deterministic and auditable. Experiments on three driving VLMs (WiseAD, DriveMM, Cosmos-Reason2-2B) show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods while maintaining diverse recommendations across the condition space. Ablations confirm both scoring components contribute, and qualitative analysis demonstrates end-to-end workflows from developer query to targeted evaluation.